Alternatives to LongLLaMA

Tülu 3 is a cutting-edge language model created by the Allen Institute for AI (Ai2) that aims to improve proficiency in fields like knowledge, reasoning, mathematics, coding, and safety. It is based on the Llama 3 Base and undergoes a detailed four-stage post-training regimen: careful prompt curation and synthesis, supervised fine-tuning on a wide array of prompts and completions, preference tuning utilizing both off- and on-policy data, and a unique reinforcement learning strategy that enhances targeted skills through measurable rewards. Notably, this open-source model sets itself apart by ensuring complete transparency, offering access to its training data, code, and evaluation tools, thus bridging the performance divide between open and proprietary fine-tuning techniques. Performance assessments reveal that Tülu 3 surpasses other models with comparable sizes, like Llama 3.1-Instruct and Qwen2.5-Instruct, across an array of benchmarks, highlighting its effectiveness. The continuous development of Tülu 3 signifies the commitment to advancing AI capabilities while promoting an open and accessible approach to technology.

Introducing the next iteration of our open-source large language model, this version features model weights along with initial code for the pretrained and fine-tuned Llama language models, which span from 7 billion to 70 billion parameters. The Llama 2 pretrained models have been developed using an impressive 2 trillion tokens and offer double the context length compared to their predecessor, Llama 1. Furthermore, the fine-tuned models have been enhanced through the analysis of over 1 million human annotations. Llama 2 demonstrates superior performance against various other open-source language models across multiple external benchmarks, excelling in areas such as reasoning, coding capabilities, proficiency, and knowledge assessments. For its training, Llama 2 utilized publicly accessible online data sources, while the fine-tuned variant, Llama-2-chat, incorporates publicly available instruction datasets along with the aforementioned extensive human annotations. Our initiative enjoys strong support from a diverse array of global stakeholders who are enthusiastic about our open approach to AI, including companies that have provided valuable early feedback and are eager to collaborate using Llama 2. The excitement surrounding Llama 2 signifies a pivotal shift in how AI can be developed and utilized collectively.

Push the limits of individual alignment, artificial consciousness, open-source software, and decentralization through experimentation that larger corporations and governments often shy away from. Hermes 3 features sophisticated long-term context retention, the ability to engage in multi-turn conversations, and intricate roleplaying and internal monologue capabilities, alongside improved functionality for agentic function-calling. The design of this model emphasizes precise adherence to system prompts and instruction sets in a flexible way. By fine-tuning Llama 3.1 across various scales, including 8B, 70B, and 405B, and utilizing a dataset largely composed of synthetically generated inputs, Hermes 3 showcases performance that rivals and even surpasses Llama 3.1, while also unlocking greater potential in reasoning and creative tasks. This series of instructive and tool-utilizing models exhibits exceptional reasoning and imaginative skills, paving the way for innovative applications. Ultimately, Hermes 3 represents a significant advancement in the landscape of AI development.

Code Llama is an advanced language model designed to generate code through text prompts, distinguishing itself as a leading tool among publicly accessible models for coding tasks. This innovative model not only streamlines workflows for existing developers but also aids beginners in overcoming challenges associated with learning to code. Its versatility positions Code Llama as both a valuable productivity enhancer and an educational resource, assisting programmers in creating more robust and well-documented software solutions. Additionally, users can generate both code and natural language explanations by providing either type of prompt, making it an adaptable tool for various programming needs. Available for free for both research and commercial applications, Code Llama is built upon Llama 2 architecture and comes in three distinct versions: the foundational Code Llama model, Code Llama - Python which is tailored specifically for Python programming, and Code Llama - Instruct, optimized for comprehending and executing natural language directives effectively.

The MiniMax‑M1 model, introduced by MiniMax AI and licensed under Apache 2.0, represents a significant advancement in hybrid-attention reasoning architecture. With an extraordinary capacity for handling a 1 million-token context window and generating outputs of up to 80,000 tokens, it facilitates in-depth analysis of lengthy texts. Utilizing a cutting-edge CISPO algorithm, MiniMax‑M1 was trained through extensive reinforcement learning, achieving completion on 512 H800 GPUs in approximately three weeks. This model sets a new benchmark in performance across various domains, including mathematics, programming, software development, tool utilization, and understanding of long contexts, either matching or surpassing the capabilities of leading models in the field. Additionally, users can choose between two distinct variants of the model, each with a thinking budget of either 40K or 80K, and access the model's weights and deployment instructions on platforms like GitHub and Hugging Face. Such features make MiniMax‑M1 a versatile tool for developers and researchers alike.

Introducing an open-source AI model that can be fine-tuned, distilled, and deployed across various platforms. Our newest instruction-tuned model comes in three sizes: 8B, 70B, and 405B, giving you options to suit different needs. With our open ecosystem, you can expedite your development process using a diverse array of tailored product offerings designed to meet your specific requirements. You have the flexibility to select between real-time inference and batch inference services according to your project's demands. Additionally, you can download model weights to enhance cost efficiency per token while fine-tuning for your application. Improve performance further by utilizing synthetic data and seamlessly deploy your solutions on-premises or in the cloud. Take advantage of Llama system components and expand the model's capabilities through zero-shot tool usage and retrieval-augmented generation (RAG) to foster agentic behaviors. By utilizing 405B high-quality data, you can refine specialized models tailored to distinct use cases, ensuring optimal functionality for your applications. Ultimately, this empowers developers to create innovative solutions that are both efficient and effective.

Introducing Mistral NeMo, our latest and most advanced small model yet, featuring a cutting-edge 12 billion parameters and an expansive context length of 128,000 tokens, all released under the Apache 2.0 license. Developed in partnership with NVIDIA, Mistral NeMo excels in reasoning, world knowledge, and coding proficiency within its category. Its architecture adheres to industry standards, making it user-friendly and a seamless alternative for systems currently utilizing Mistral 7B. To facilitate widespread adoption among researchers and businesses, we have made available both pre-trained base and instruction-tuned checkpoints under the same Apache license. Notably, Mistral NeMo incorporates quantization awareness, allowing for FP8 inference without compromising performance. The model is also tailored for diverse global applications, adept in function calling and boasting a substantial context window. When compared to Mistral 7B, Mistral NeMo significantly outperforms in understanding and executing detailed instructions, showcasing enhanced reasoning skills and the ability to manage complex multi-turn conversations. Moreover, its design positions it as a strong contender for multi-lingual tasks, ensuring versatility across various use cases.

Llama (Large Language Model Meta AI) stands as a cutting-edge foundational large language model aimed at helping researchers push the boundaries of their work within this area of artificial intelligence. By providing smaller yet highly effective models like Llama, the research community can benefit even if they lack extensive infrastructure, thus promoting greater accessibility in this dynamic and rapidly evolving domain. Creating smaller foundational models such as Llama is advantageous in the landscape of large language models, as it demands significantly reduced computational power and resources, facilitating the testing of innovative methods, confirming existing research, and investigating new applications. These foundational models leverage extensive unlabeled datasets, making them exceptionally suitable for fine-tuning across a range of tasks. We are offering Llama in multiple sizes (7B, 13B, 33B, and 65B parameters), accompanied by a detailed Llama model card that outlines our development process while adhering to our commitment to Responsible AI principles. By making these resources available, we aim to empower a broader segment of the research community to engage with and contribute to advancements in AI.

Qwen3-Max represents Alibaba's cutting-edge large language model, featuring a staggering trillion parameters aimed at enhancing capabilities in tasks that require agency, coding, reasoning, and managing lengthy contexts. This model is an evolution of the Qwen3 series, leveraging advancements in architecture, training methods, and inference techniques; it integrates both thinker and non-thinker modes, incorporates a unique “thinking budget” system, and allows for dynamic mode adjustments based on task complexity. Capable of handling exceptionally lengthy inputs, processing hundreds of thousands of tokens, it also supports tool invocation and demonstrates impressive results across various benchmarks, including coding, multi-step reasoning, and agent evaluations like Tau2-Bench. While the initial version prioritizes instruction adherence in a non-thinking mode, Alibaba is set to introduce reasoning functionalities that will facilitate autonomous agent operations in the future. In addition to its existing multilingual capabilities and extensive training on trillions of tokens, Qwen3-Max is accessible through API interfaces that align seamlessly with OpenAI-style functionalities, ensuring broad usability across applications. This comprehensive framework positions Qwen3-Max as a formidable player in the realm of advanced artificial intelligence language models.

Llama 4 Scout is an advanced multimodal AI model with 17 billion active parameters, offering industry-leading performance with a 10 million token context length. This enables it to handle complex tasks like multi-document summarization and detailed code reasoning with impressive accuracy. Scout surpasses previous Llama models in both text and image understanding, making it an excellent choice for applications that require a combination of language processing and image analysis. Its powerful capabilities in long-context tasks and image-grounding applications set it apart from other models in its class, providing superior results for a wide range of industries.

We are excited to present MPT-7B, the newest addition to the MosaicML Foundation Series. This transformer model has been meticulously trained from the ground up using 1 trillion tokens of diverse text and code. It is open-source and ready for commercial applications, delivering performance on par with LLaMA-7B. The training process took 9.5 days on the MosaicML platform, requiring no human input and incurring an approximate cost of $200,000. With MPT-7B, you can now train, fine-tune, and launch your own customized MPT models, whether you choose to begin with one of our provided checkpoints or start anew. To provide additional options, we are also introducing three fine-tuned variants alongside the base MPT-7B: MPT-7B-Instruct, MPT-7B-Chat, and MPT-7B-StoryWriter-65k+, the latter boasting an impressive context length of 65,000 tokens, allowing for extensive content generation. These advancements open up new possibilities for developers and researchers looking to leverage the power of transformer models in their projects.

Mistral 7B is a language model with 7.3 billion parameters that demonstrates superior performance compared to larger models such as Llama 2 13B on a variety of benchmarks. It utilizes innovative techniques like Grouped-Query Attention (GQA) for improved inference speed and Sliding Window Attention (SWA) to manage lengthy sequences efficiently. Released under the Apache 2.0 license, Mistral 7B is readily available for deployment on different platforms, including both local setups and prominent cloud services. Furthermore, a specialized variant known as Mistral 7B Instruct has shown remarkable capabilities in following instructions, outperforming competitors like Llama 2 13B Chat in specific tasks. This versatility makes Mistral 7B an attractive option for developers and researchers alike.

Stability AI, along with its CarperAI lab, is excited to unveil Stable Beluga 1 and its advanced successor, Stable Beluga 2, previously known as FreeWilly, both of which are robust new Large Language Models (LLMs) available for public use. These models exhibit remarkable reasoning capabilities across a wide range of benchmarks, showcasing their versatility and strength. Stable Beluga 1 is built on the original LLaMA 65B foundation model and has undergone meticulous fine-tuning with a novel synthetically-generated dataset utilizing Supervised Fine-Tune (SFT) in the conventional Alpaca format. In a similar vein, Stable Beluga 2 utilizes the LLaMA 2 70B foundation model, pushing the boundaries of performance in the industry. Their development marks a significant step forward in the evolution of open access AI technologies.

StarCoder and StarCoderBase represent advanced Large Language Models specifically designed for code, developed using openly licensed data from GitHub, which encompasses over 80 programming languages, Git commits, GitHub issues, and Jupyter notebooks. In a manner akin to LLaMA, we constructed a model with approximately 15 billion parameters trained on a staggering 1 trillion tokens. Furthermore, we tailored the StarCoderBase model with 35 billion Python tokens, leading to the creation of what we now refer to as StarCoder. Our evaluations indicated that StarCoderBase surpasses other existing open Code LLMs when tested against popular programming benchmarks and performs on par with or even exceeds proprietary models like code-cushman-001 from OpenAI, the original Codex model that fueled early iterations of GitHub Copilot. With an impressive context length exceeding 8,000 tokens, the StarCoder models possess the capability to handle more information than any other open LLM, thus paving the way for a variety of innovative applications. This versatility is highlighted by our ability to prompt the StarCoder models through a sequence of dialogues, effectively transforming them into dynamic technical assistants that can provide support in diverse programming tasks.

GPT-4.1 mini is a streamlined version of GPT-4.1, offering the same core capabilities in coding, instruction adherence, and long-context comprehension, but with faster performance and lower costs. Ideal for developers seeking to integrate AI into real-time applications, GPT-4.1 mini maintains a 1 million token context window and is well-suited for tasks that demand low-latency responses. It is a cost-effective option for businesses that need powerful AI capabilities without the high overhead associated with larger models.

OpenLLaMA is an openly licensed reproduction of Meta AI's LLaMA 7B, developed using the RedPajama dataset. The model weights we offer can seamlessly replace the LLaMA 7B in current applications. Additionally, we have created a more compact 3B version of the LLaMA model for those seeking a lighter alternative. This provides users with more flexibility in choosing the right model for their specific needs.

Falcon-40B is a causal decoder-only model consisting of 40 billion parameters, developed by TII and trained on 1 trillion tokens from RefinedWeb, supplemented with carefully selected datasets. It is distributed under the Apache 2.0 license. Why should you consider using Falcon-40B? This model stands out as the leading open-source option available, surpassing competitors like LLaMA, StableLM, RedPajama, and MPT, as evidenced by its ranking on the OpenLLM Leaderboard. Its design is specifically tailored for efficient inference, incorporating features such as FlashAttention and multiquery capabilities. Moreover, it is offered under a flexible Apache 2.0 license, permitting commercial applications without incurring royalties or facing restrictions. It's important to note that this is a raw, pretrained model and is generally recommended to be fine-tuned for optimal performance in most applications. If you need a version that is more adept at handling general instructions in a conversational format, you might want to explore Falcon-40B-Instruct as a potential alternative.

The TinyLlama initiative seeks to pretrain a Llama model with 1.1 billion parameters using a dataset of 3 trillion tokens. With the right optimizations, this ambitious task can be completed in a mere 90 days, utilizing 16 A100-40G GPUs. We have maintained the same architecture and tokenizer as Llama 2, ensuring that TinyLlama is compatible with various open-source projects that are based on Llama. Additionally, the model's compact design, consisting of just 1.1 billion parameters, makes it suitable for numerous applications that require limited computational resources and memory. This versatility enables developers to integrate TinyLlama seamlessly into their existing frameworks and workflows.

LTM-2-mini operates with a context of 100 million tokens, which is comparable to around 10 million lines of code or roughly 750 novels. This model employs a sequence-dimension algorithm that is approximately 1000 times more cost-effective per decoded token than the attention mechanism used in Llama 3.1 405B when handling a 100 million token context window. Furthermore, the disparity in memory usage is significantly greater; utilizing Llama 3.1 405B with a 100 million token context necessitates 638 H100 GPUs per user solely for maintaining a single 100 million token key-value cache. Conversely, LTM-2-mini requires only a minuscule portion of a single H100's high-bandwidth memory for the same context, demonstrating its efficiency. This substantial difference makes LTM-2-mini an appealing option for applications needing extensive context processing without the hefty resource demands.

PygmalionAI is a vibrant community focused on the development of open-source initiatives utilizing EleutherAI's GPT-J 6B and Meta's LLaMA models. Essentially, Pygmalion specializes in crafting AI tailored for engaging conversations and roleplaying. The actively maintained Pygmalion AI model currently features the 7B variant, derived from Meta AI's LLaMA model. Requiring a mere 18GB (or even less) of VRAM, Pygmalion demonstrates superior chat functionality compared to significantly larger language models, all while utilizing relatively limited resources. Our meticulously assembled dataset, rich in high-quality roleplaying content, guarantees that your AI companion will be the perfect partner for roleplaying scenarios. Both the model weights and the training code are entirely open-source, allowing you the freedom to modify and redistribute them for any purpose you desire. Generally, language models, such as Pygmalion, operate on GPUs, as they require swift memory access and substantial processing power to generate coherent text efficiently. As a result, users can expect a smooth and responsive interaction experience when employing Pygmalion's capabilities.

Vicuna-13B is an open-source conversational agent developed through the fine-tuning of LLaMA, utilizing a dataset of user-shared dialogues gathered from ShareGPT. Initial assessments, with GPT-4 serving as an evaluator, indicate that Vicuna-13B achieves over 90% of the quality exhibited by OpenAI's ChatGPT and Google Bard, and it surpasses other models such as LLaMA and Stanford Alpaca in more than 90% of instances. The entire training process for Vicuna-13B incurs an estimated expenditure of approximately $300. Additionally, the source code and model weights, along with an interactive demonstration, are made available for public access under non-commercial terms, fostering a collaborative environment for further development and exploration. This openness encourages innovation and enables users to experiment with the model's capabilities in diverse applications.

OLMo 2 represents a collection of completely open language models created by the Allen Institute for AI (AI2), aimed at giving researchers and developers clear access to training datasets, open-source code, reproducible training methodologies, and thorough assessments. These models are trained on an impressive volume of up to 5 trillion tokens and compete effectively with top open-weight models like Llama 3.1, particularly in English academic evaluations. A key focus of OLMo 2 is on ensuring training stability, employing strategies to mitigate loss spikes during extended training periods, and applying staged training interventions in the later stages of pretraining to mitigate weaknesses in capabilities. Additionally, the models leverage cutting-edge post-training techniques derived from AI2's Tülu 3, leading to the development of OLMo 2-Instruct models. To facilitate ongoing enhancements throughout the development process, an actionable evaluation framework known as the Open Language Modeling Evaluation System (OLMES) was created, which includes 20 benchmarks that evaluate essential capabilities. This comprehensive approach not only fosters transparency but also encourages continuous improvement in language model performance.

The Mixtral 8x7B model is an advanced sparse mixture of experts (SMoE) system that boasts open weights and is released under the Apache 2.0 license. This model demonstrates superior performance compared to Llama 2 70B across various benchmarks while achieving inference speeds that are six times faster. Recognized as the leading open-weight model with a flexible licensing framework, Mixtral also excels in terms of cost-efficiency and performance. Notably, it competes with and often surpasses GPT-3.5 in numerous established benchmarks, highlighting its significance in the field. Its combination of accessibility, speed, and effectiveness makes it a compelling choice for developers seeking high-performing AI solutions.

GPT-4.1 represents a significant upgrade in generative AI, with notable advancements in coding, instruction adherence, and handling long contexts. This model supports up to 1 million tokens of context, allowing it to tackle complex, multi-step tasks across various domains. GPT-4.1 outperforms earlier models in key benchmarks, particularly in coding accuracy, and is designed to streamline workflows for developers and businesses by improving task completion speed and reliability.

We are excited to announce the launch of our X1 large series of models. The most robust model from Giga ML is now accessible for both pre-training and fine-tuning in an on-premises environment. Thanks to our compatibility with Open AI, existing integrations with tools like long chain, llama-index, and others function effortlessly. You can also proceed with pre-training LLMs using specialized data sources such as industry-specific documents or company files. The landscape of large language models (LLMs) is rapidly evolving, creating incredible opportunities for advancements in natural language processing across multiple fields. Despite this growth, several significant challenges persist in the industry. At Giga ML, we are thrilled to introduce the X1 Large 32k model, an innovative on-premise LLM solution designed specifically to tackle these pressing challenges, ensuring that organizations can harness the full potential of LLMs effectively. With this launch, we aim to empower businesses to elevate their language processing capabilities.

Qwen2.5-1M, an open-source language model from the Qwen team, has been meticulously crafted to manage context lengths reaching as high as one million tokens. This version introduces two distinct model variants, namely Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1M, representing a significant advancement as it is the first instance of Qwen models being enhanced to accommodate such large context lengths. In addition to this, the team has released an inference framework that is based on vLLM and incorporates sparse attention mechanisms, which greatly enhance the processing speed for 1M-token inputs, achieving improvements between three to seven times. A detailed technical report accompanies this release, providing in-depth insights into the design choices and the results from various ablation studies. This transparency allows users to fully understand the capabilities and underlying technology of the models.

Kimi K2 represents a cutting-edge series of open-source large language models utilizing a mixture-of-experts (MoE) architecture, with a staggering 1 trillion parameters in total and 32 billion activated parameters tailored for optimized task execution. Utilizing the Muon optimizer, it has been trained on a substantial dataset of over 15.5 trillion tokens, with its performance enhanced by MuonClip’s attention-logit clamping mechanism, resulting in remarkable capabilities in areas such as advanced knowledge comprehension, logical reasoning, mathematics, programming, and various agentic operations. Moonshot AI offers two distinct versions: Kimi-K2-Base, designed for research-level fine-tuning, and Kimi-K2-Instruct, which is pre-trained for immediate applications in chat and tool interactions, facilitating both customized development and seamless integration of agentic features. Comparative benchmarks indicate that Kimi K2 surpasses other leading open-source models and competes effectively with top proprietary systems, particularly excelling in coding and intricate task analysis. Furthermore, it boasts a generous context length of 128 K tokens, compatibility with tool-calling APIs, and support for industry-standard inference engines, making it a versatile option for various applications. The innovative design and features of Kimi K2 position it as a significant advancement in the field of artificial intelligence language processing.

Xgen-small is a compact language model crafted by Salesforce AI Research that is tailored for enterprise use, offering efficient long-context capabilities at a manageable cost. It employs a combination of focused data curation, scalable pre-training, length extension, instruction fine-tuning, and reinforcement learning to address the intricate and high-volume inference needs of contemporary businesses. In contrast to conventional large models, Xgen-small excels in processing extensive contexts, allowing it to effectively synthesize insights from various sources such as internal documents, code bases, research articles, and real-time data feeds. With parameter sizes of 4B and 9B, it strikes a careful balance between cost efficiency, privacy protections, and comprehensive long-context comprehension, positioning itself as a reliable and sustainable option for large-scale Enterprise AI implementation. This innovative approach not only enhances operational efficiency but also empowers organizations to leverage AI effectively in their strategic initiatives.

CodeQwen serves as the coding counterpart to Qwen, which is a series of large language models created by the Qwen team at Alibaba Cloud. Built on a transformer architecture that functions solely as a decoder, this model has undergone extensive pre-training using a vast dataset of code. It showcases robust code generation abilities and demonstrates impressive results across various benchmarking tests. With the capacity to comprehend and generate long contexts of up to 64,000 tokens, CodeQwen accommodates 92 programming languages and excels in tasks such as text-to-SQL queries and debugging. Engaging with CodeQwen is straightforward—you can initiate a conversation with just a few lines of code utilizing transformers. The foundation of this interaction relies on constructing the tokenizer and model using pre-existing methods, employing the generate function to facilitate dialogue guided by the chat template provided by the tokenizer. In alignment with our established practices, we implement the ChatML template tailored for chat models. This model adeptly completes code snippets based on the prompts it receives, delivering responses without the need for any further formatting adjustments, thereby enhancing the user experience. The seamless integration of these elements underscores the efficiency and versatility of CodeQwen in handling diverse coding tasks.

Canopy Labs has unveiled Orpheus, an innovative suite of advanced speech large language models (LLMs) aimed at achieving human-like speech generation capabilities. Utilizing the Llama-3 architecture, these models have been trained on an extensive dataset comprising over 100,000 hours of English speech, allowing them to generate speech that exhibits natural intonation, emotional depth, and rhythmic flow that outperforms existing high-end closed-source alternatives. Orpheus also features zero-shot voice cloning, enabling users to mimic voices without any need for prior fine-tuning, and provides easy-to-use tags for controlling emotion and intonation. The models are engineered for low latency, achieving approximately 200ms streaming latency for real-time usage, which can be further decreased to around 100ms when utilizing input streaming. Canopy Labs has made available both pre-trained and fine-tuned models with 3 billion parameters under the flexible Apache 2.0 license, with future intentions to offer smaller models with 1 billion, 400 million, and 150 million parameters to cater to devices with limited resources. This strategic move is expected to broaden accessibility and application potential across various platforms and use cases.

Yi-Lightning, a product of 01.AI and spearheaded by Kai-Fu Lee, marks a significant leap forward in the realm of large language models, emphasizing both performance excellence and cost-effectiveness. With the ability to process a context length of up to 16K tokens, it offers an attractive pricing model of $0.14 per million tokens for both inputs and outputs, making it highly competitive in the market. The model employs an improved Mixture-of-Experts (MoE) framework, featuring detailed expert segmentation and sophisticated routing techniques that enhance its training and inference efficiency. Yi-Lightning has distinguished itself across multiple fields, achieving top distinctions in areas such as Chinese language processing, mathematics, coding tasks, and challenging prompts on chatbot platforms, where it ranked 6th overall and 9th in style control. Its creation involved an extensive combination of pre-training, targeted fine-tuning, and reinforcement learning derived from human feedback, which not only enhances its performance but also prioritizes user safety. Furthermore, the model's design includes significant advancements in optimizing both memory consumption and inference speed, positioning it as a formidable contender in its field.

OpenAI’s GPT-5 mini is a cost-efficient, faster version of the flagship GPT-5 model, designed to handle well-defined tasks and precise inputs with high reasoning capabilities. Supporting text and image inputs, GPT-5 mini can process and generate large amounts of content thanks to its extensive 400,000-token context window and a maximum output of 128,000 tokens. This model is optimized for speed, making it ideal for developers and businesses needing quick turnaround times on natural language processing tasks while maintaining accuracy. The pricing model offers significant savings, charging $0.25 per million input tokens and $2 per million output tokens, compared to the higher costs of the full GPT-5. It supports many advanced API features such as streaming responses, function calling, and fine-tuning, while excluding audio input and image generation capabilities. GPT-5 mini is compatible with a broad range of API endpoints including chat completions, real-time responses, and embeddings, making it highly flexible. Rate limits vary by usage tier, supporting from hundreds to tens of thousands of requests per minute, ensuring reliability for different scale needs. This model strikes a balance between performance and cost, suitable for applications requiring fast, high-quality AI interaction without extensive resource use.

The latest iteration of the open-source AI model, which can be fine-tuned and deployed in various environments, is now offered in multiple versions, including 1B, 3B, 11B, and 90B, alongside the option to continue utilizing Llama 3.1. Llama 3.2 comprises a series of large language models (LLMs) that come pretrained and fine-tuned in 1B and 3B configurations for multilingual text only, while the 11B and 90B models accommodate both text and image inputs, producing text outputs. With this new release, you can create highly effective and efficient applications tailored to your needs. For on-device applications, such as summarizing phone discussions or accessing calendar tools, the 1B or 3B models are ideal choices. Meanwhile, the 11B or 90B models excel in image-related tasks, enabling you to transform existing images or extract additional information from images of your environment. Overall, this diverse range of models allows developers to explore innovative use cases across various domains.

Phi-4-mini-reasoning is a transformer-based language model with 3.8 billion parameters, specifically designed to excel in mathematical reasoning and methodical problem-solving within environments that have limited computational capacity or latency constraints. Its optimization stems from fine-tuning with synthetic data produced by the DeepSeek-R1 model, striking a balance between efficiency and sophisticated reasoning capabilities. With training that encompasses over one million varied math problems, ranging in complexity from middle school to Ph.D. level, Phi-4-mini-reasoning demonstrates superior performance to its base model in generating lengthy sentences across multiple assessments and outshines larger counterparts such as OpenThinker-7B, Llama-3.2-3B-instruct, and DeepSeek-R1. Equipped with a 128K-token context window, it also facilitates function calling, which allows for seamless integration with various external tools and APIs. Moreover, Phi-4-mini-reasoning can be quantized through the Microsoft Olive or Apple MLX Framework, enabling its deployment on a variety of edge devices, including IoT gadgets, laptops, and smartphones. Its design not only enhances user accessibility but also expands the potential for innovative applications in mathematical fields.

Introducing DeepSeek-V3.2-Exp, our newest experimental model derived from V3.1-Terminus, featuring the innovative DeepSeek Sparse Attention (DSA) that enhances both training and inference speed for lengthy contexts. This DSA mechanism allows for precise sparse attention while maintaining output quality, leading to improved performance for tasks involving long contexts and a decrease in computational expenses. Benchmark tests reveal that V3.2-Exp matches the performance of V3.1-Terminus while achieving these efficiency improvements. The model is now fully operational across app, web, and API platforms. Additionally, to enhance accessibility, we have slashed DeepSeek API prices by over 50% effective immediately. During a transition period, users can still utilize V3.1-Terminus via a temporary API endpoint until October 15, 2025. DeepSeek encourages users to share their insights regarding DSA through our feedback portal. Complementing the launch, DeepSeek-V3.2-Exp has been made open-source, with model weights and essential technology—including crucial GPU kernels in TileLang and CUDA—accessible on Hugging Face. We look forward to seeing how the community engages with this advancement.

Mistral Small 3.1 represents a cutting-edge, multimodal, and multilingual AI model that has been released under the Apache 2.0 license. This upgraded version builds on Mistral Small 3, featuring enhanced text capabilities and superior multimodal comprehension, while also accommodating an extended context window of up to 128,000 tokens. It demonstrates superior performance compared to similar models such as Gemma 3 and GPT-4o Mini, achieving impressive inference speeds of 150 tokens per second. Tailored for adaptability, Mistral Small 3.1 shines in a variety of applications, including instruction following, conversational support, image analysis, and function execution, making it ideal for both business and consumer AI needs. The model's streamlined architecture enables it to operate efficiently on hardware such as a single RTX 4090 or a Mac equipped with 32GB of RAM, thus supporting on-device implementations. Users can download it from Hugging Face and access it through Mistral AI's developer playground, while it is also integrated into platforms like Google Cloud Vertex AI, with additional accessibility on NVIDIA NIM and more. This flexibility ensures that developers can leverage its capabilities across diverse environments and applications.

Voxtral models represent cutting-edge open-source systems designed for speech understanding, available in two sizes: a larger 24 B variant aimed at production-scale use and a smaller 3 B variant suitable for local and edge applications, both of which are provided under the Apache 2.0 license. These models excel in delivering precise transcription while featuring inherent semantic comprehension, accommodating long-form contexts of up to 32 K tokens and incorporating built-in question-and-answer capabilities along with structured summarization. They automatically detect languages across a range of major tongues and enable direct function-calling to activate backend workflows through voice commands. Retaining the textual strengths of their Mistral Small 3.1 architecture, Voxtral can process audio inputs of up to 30 minutes for transcription tasks and up to 40 minutes for comprehension, consistently surpassing both open-source and proprietary competitors in benchmarks like LibriSpeech, Mozilla Common Voice, and FLEURS. Users can access Voxtral through downloads on Hugging Face, API endpoints, or by utilizing private on-premises deployments, and the model also provides options for domain-specific fine-tuning along with advanced features tailored for enterprise needs, thus enhancing its applicability across various sectors.

Sky-T1-32B-Preview is an innovative open-source reasoning model crafted by the NovaSky team at UC Berkeley's Sky Computing Lab. It delivers performance comparable to proprietary models such as o1-preview on various reasoning and coding assessments, while being developed at a cost of less than $450, highlighting the potential for budget-friendly, advanced reasoning abilities. Fine-tuned from Qwen2.5-32B-Instruct, the model utilized a meticulously curated dataset comprising 17,000 examples spanning multiple fields, such as mathematics and programming. The entire training process was completed in just 19 hours using eight H100 GPUs with DeepSpeed Zero-3 offloading technology. Every component of this initiative—including the data, code, and model weights—is entirely open-source, allowing both academic and open-source communities to not only replicate but also improve upon the model's capabilities. This accessibility fosters collaboration and innovation in the realm of artificial intelligence research and development.

Scale AI is excited to introduce Defense Llama, a specialized Large Language Model (LLM) developed from Meta’s Llama 3, tailored specifically to enhance American national security initiatives. Designed for exclusive use within controlled U.S. government settings through Scale Donovan, Defense Llama equips our military personnel and national security experts with the generative AI tools needed for various applications, including the planning of military operations and the analysis of adversary weaknesses. With its training grounded in a comprehensive array of materials, including military doctrines and international humanitarian laws, Defense Llama adheres to the Department of Defense (DoD) guidelines on armed conflict and aligns with the DoD’s Ethical Principles for Artificial Intelligence. This structured foundation allows the model to deliver precise, relevant, and insightful responses tailored to the needs of its users. By providing a secure and efficient generative AI platform, Scale is committed to enhancing the capabilities of U.S. defense personnel in their critical missions. The integration of such technology marks a significant advancement in how national security objectives can be achieved.

Teuken-7B is a multilingual language model that has been developed as part of the OpenGPT-X initiative, specifically tailored to meet the needs of Europe's varied linguistic environment. This model has been trained on a dataset where over half consists of non-English texts, covering all 24 official languages of the European Union, which ensures it performs well across these languages. A significant advancement in Teuken-7B is its unique multilingual tokenizer, which has been fine-tuned for European languages, leading to enhanced training efficiency and lower inference costs when compared to conventional monolingual tokenizers. Users can access two versions of the model: Teuken-7B-Base, which serves as the basic pre-trained version, and Teuken-7B-Instruct, which has received instruction tuning aimed at boosting its ability to respond to user requests. Both models are readily available on Hugging Face, fostering an environment of transparency and collaboration within the artificial intelligence community while also encouraging further innovation. The creation of Teuken-7B highlights a dedication to developing AI solutions that embrace and represent the rich diversity found across Europe.

Instruction-following models like GPT-3.5 (text-DaVinci-003), ChatGPT, Claude, and Bing Chat have seen significant advancements in their capabilities, leading to a rise in their usage among individuals in both personal and professional contexts. Despite their growing popularity and integration into daily tasks, these models are not without their shortcomings, as they can sometimes disseminate inaccurate information, reinforce harmful stereotypes, and use inappropriate language. To effectively tackle these critical issues, it is essential for researchers and scholars to become actively involved in exploring these models further. However, conducting research on instruction-following models within academic settings has posed challenges due to the unavailability of models with comparable functionality to proprietary options like OpenAI’s text-DaVinci-003. In response to this gap, we are presenting our insights on an instruction-following language model named Alpaca, which has been fine-tuned from Meta’s LLaMA 7B model, aiming to contribute to the discourse and development in this field. This initiative represents a step towards enhancing the understanding and capabilities of instruction-following models in a more accessible manner for researchers.

Devstral is a collaborative effort between Mistral AI and All Hands AI, resulting in an open-source large language model specifically tailored for software engineering. This model demonstrates remarkable proficiency in navigating intricate codebases, managing edits across numerous files, and addressing practical problems, achieving a notable score of 46.8% on the SWE-Bench Verified benchmark, which is superior to all other open-source models. Based on Mistral-Small-3.1, Devstral boasts an extensive context window supporting up to 128,000 tokens. It is designed for optimal performance on high-performance hardware setups, such as Macs equipped with 32GB of RAM or Nvidia RTX 4090 GPUs, and supports various inference frameworks including vLLM, Transformers, and Ollama. Released under the Apache 2.0 license, Devstral is freely accessible on platforms like Hugging Face, Ollama, Kaggle, Unsloth, and LM Studio, allowing developers to integrate its capabilities into their projects seamlessly. This model not only enhances productivity for software engineers but also serves as a valuable resource for anyone working with code.

Foundation models, including GPT-4, have significantly accelerated advancements in artificial intelligence, yet the most advanced models remain either proprietary or only partially accessible. In response to this challenge, the RedPajama initiative aims to develop a collection of top-tier, fully open-source models. We are thrilled to announce that we have successfully completed the initial phase of this endeavor: recreating the LLaMA training dataset, which contains over 1.2 trillion tokens. Currently, many of the leading foundation models are locked behind commercial APIs, restricting opportunities for research, customization, and application with sensitive information. The development of fully open-source models represents a potential solution to these limitations, provided that the open-source community can bridge the gap in quality between open and closed models. Recent advancements have shown promising progress in this area, suggesting that the AI field is experiencing a transformative period akin to the emergence of Linux. The success of Stable Diffusion serves as a testament to the fact that open-source alternatives can not only match the quality of commercial products like DALL-E but also inspire remarkable creativity through the collaborative efforts of diverse communities. By fostering an open-source ecosystem, we can unlock new possibilities for innovation and ensure broader access to cutting-edge AI technology.

Llama 4 Behemoth, with 288 billion active parameters, is Meta's flagship AI model, setting new standards for multimodal performance. Outpacing its predecessors like GPT-4.5 and Claude Sonnet 3.7, it leads the field in STEM benchmarks, offering cutting-edge results in tasks such as problem-solving and reasoning. Designed as the teacher model for the Llama 4 series, Behemoth drives significant improvements in model quality and efficiency through distillation. Although still in development, Llama 4 Behemoth is shaping the future of AI with its unparalleled intelligence, particularly in math, image, and multilingual tasks.

The newest version in the Llama series, Llama 3.3, represents a significant advancement in language models aimed at enhancing AI's capabilities in understanding and communication. It boasts improved contextual reasoning, superior language generation, and advanced fine-tuning features aimed at producing exceptionally accurate, human-like responses across a variety of uses. This iteration incorporates a more extensive training dataset, refined algorithms for deeper comprehension, and mitigated biases compared to earlier versions. Llama 3.3 stands out in applications including natural language understanding, creative writing, technical explanations, and multilingual interactions, making it a crucial asset for businesses, developers, and researchers alike. Additionally, its modular architecture facilitates customizable deployment in specific fields, ensuring it remains versatile and high-performing even in large-scale applications. With these enhancements, Llama 3.3 is poised to redefine the standards of AI language models.