List of the Top On-Prem Small Language Models in 2026

Mistral AI is recognized as a pioneering startup in the field of artificial intelligence, with a particular emphasis on open-source generative technologies. The company offers a wide range of customizable, enterprise-grade AI solutions that can be deployed across multiple environments, including on-premises, cloud, edge, and individual devices. Notable among their offerings are "Le Chat," a multilingual AI assistant designed to enhance productivity in both personal and business contexts, and "La Plateforme," a resource for developers that streamlines the creation and implementation of AI-powered applications. Mistral AI's unwavering dedication to transparency and innovative practices has enabled it to carve out a significant niche as an independent AI laboratory, where it plays an active role in the evolution of open-source AI while also influencing relevant policy conversations. By championing the development of an open AI ecosystem, Mistral AI not only contributes to technological advancements but also positions itself as a leading voice within the industry, shaping the future of artificial intelligence. This commitment to fostering collaboration and openness within the AI community further solidifies its reputation as a forward-thinking organization.

Gemma 4 is a modern AI model introduced by Google and built on the Gemini architecture to provide enhanced performance and flexibility for developers and researchers. The model is designed to run efficiently on a single GPU or TPU, which makes powerful AI capabilities more accessible without requiring large-scale infrastructure. Gemma 4 focuses heavily on improving natural language understanding and text generation, enabling it to support a wide range of AI-powered applications. These capabilities allow developers to build systems such as conversational assistants, intelligent search tools, and automated content generation platforms. The architecture behind Gemma 4 enables the model to process language with greater accuracy while maintaining efficient computational requirements. This balance between performance and efficiency allows developers to experiment with advanced AI features without the need for extremely large computing environments. Gemma 4 is designed to be scalable so it can support both small development projects and larger enterprise applications. Researchers can also use the model to explore new approaches to machine learning and language processing. The model’s ability to run on widely available hardware makes it practical for organizations that want to integrate AI into their workflows. By combining strong language capabilities with efficient deployment requirements, Gemma 4 helps broaden access to advanced AI technology. Its design reflects a growing focus on creating models that are both powerful and practical for real-world use. As a result, Gemma 4 supports the continued expansion of AI applications across industries and research fields.

Mistral 7B is a cutting-edge language model boasting 7.3 billion parameters, which excels in various benchmarks, even surpassing larger models such as Llama 2 13B. It employs advanced methods like Grouped-Query Attention (GQA) to enhance inference speed and Sliding Window Attention (SWA) to effectively handle extensive sequences. Available under the Apache 2.0 license, Mistral 7B can be deployed across multiple platforms, including local infrastructures and major cloud services. Additionally, a unique variant called Mistral 7B Instruct has demonstrated exceptional abilities in task execution, consistently outperforming rivals like Llama 2 13B Chat in certain applications. This adaptability and performance make Mistral 7B a compelling choice for both developers and researchers seeking efficient solutions. Its innovative features and strong results highlight the model's potential impact on natural language processing projects.

Mistral AI has introduced two state-of-the-art models aimed at on-device computing and edge applications, collectively known as "les Ministraux": Ministral 3B and Ministral 8B. These advanced models set new benchmarks for knowledge, commonsense reasoning, function-calling, and efficiency in the sub-10B category. They offer remarkable flexibility for a variety of applications, from overseeing complex workflows to creating specialized task-oriented agents. With the capability to manage an impressive context length of up to 128k (currently supporting 32k on vLLM), Ministral 8B features a distinctive interleaved sliding-window attention mechanism that boosts both speed and memory efficiency during inference. Crafted for low-latency and compute-efficient applications, these models thrive in environments such as offline translation, internet-independent smart assistants, local data processing, and autonomous robotics. Additionally, when integrated with larger language models like Mistral Large, les Ministraux can serve as effective intermediaries, enhancing function-calling within detailed multi-step workflows. This synergy not only amplifies performance but also extends the potential of AI in edge computing, paving the way for innovative solutions in various fields. The introduction of these models marks a significant step forward in making advanced AI more accessible and efficient for real-world applications.

Mistral AI has introduced two advanced models tailored for on-device computing and edge applications, collectively known as "les Ministraux": Ministral 3B and Ministral 8B. These models are particularly remarkable for their abilities in knowledge retention, commonsense reasoning, function-calling, and overall operational efficiency, all while being under the 10B parameter threshold. With support for an impressive context length of up to 128k, they cater to a wide array of applications, including on-device translation, offline smart assistants, local analytics, and autonomous robotics. A standout feature of the Ministral 8B is its incorporation of an interleaved sliding-window attention mechanism, which significantly boosts both the speed and memory efficiency during inference. Both models excel in acting as intermediaries in intricate multi-step workflows, adeptly managing tasks such as input parsing, task routing, and API interactions according to user intentions while keeping latency and operational costs to a minimum. Benchmark results indicate that les Ministraux consistently outperform comparable models across numerous tasks, further cementing their competitive edge in the market. As of October 16, 2024, these innovative models are accessible to developers and businesses, with the Ministral 8B priced competitively at $0.1 per million tokens used. This pricing model promotes accessibility for users eager to incorporate sophisticated AI functionalities into their projects, potentially revolutionizing how AI is utilized in everyday applications.

On September 17, 2024, Mistral AI announced a series of important enhancements aimed at making their AI products more accessible and efficient. Among these advancements, they introduced a free tier on "La Plateforme," their serverless platform that facilitates the tuning and deployment of Mistral models as API endpoints, enabling developers to experiment and create without any cost. Additionally, Mistral AI implemented significant price reductions across their entire model lineup, featuring a striking 50% reduction for Mistral Nemo and an astounding 80% decrease for Mistral Small and Codestral, making sophisticated AI solutions much more affordable for a larger audience. Furthermore, the company unveiled Mistral Small v24.09, a model boasting 22 billion parameters, which offers an excellent balance between performance and efficiency, suitable for a range of applications such as translation, summarization, and sentiment analysis. They also launched Pixtral 12B, a vision-capable model with advanced image understanding functionalities, available for free on "Le Chat," which allows users to analyze and caption images while ensuring strong text-based performance. These updates not only showcase Mistral AI's dedication to enhancing their offerings but also underscore their mission to make cutting-edge AI technology accessible to developers across the globe. This commitment to accessibility and innovation positions Mistral AI as a leader in the AI industry.

GPT-J is an advanced language model created by EleutherAI, recognized for its remarkable abilities. In terms of performance, GPT-J demonstrates a level of proficiency that competes with OpenAI's renowned GPT-3 across a range of zero-shot tasks. Impressively, it has surpassed GPT-3 in certain aspects, particularly in code generation. The latest iteration, named GPT-J-6B, is built on an extensive linguistic dataset known as The Pile, which is publicly available and comprises a massive 825 gibibytes of language data organized into 22 distinct subsets. While GPT-J shares some characteristics with ChatGPT, it is essential to note that its primary focus is on text prediction rather than serving as a chatbot. Additionally, a significant development occurred in March 2023 when Databricks introduced Dolly, a model designed to follow instructions and operating under an Apache license, which further enhances the array of available language models. This ongoing progression in AI technology is instrumental in expanding the possibilities within the realm of natural language processing. As these models evolve, they continue to reshape how we interact with and utilize language in various applications.

The Falcon-7B model is a causal decoder-only architecture with a total of 7 billion parameters, created by TII, and trained on a vast dataset consisting of 1,500 billion tokens from RefinedWeb, along with additional carefully curated corpora, all under the Apache 2.0 license. What are the benefits of using Falcon-7B? This model excels compared to other open-source options like MPT-7B, StableLM, and RedPajama, primarily because of its extensive training on an unimaginably large dataset of 1,500 billion tokens from RefinedWeb, supplemented by thoughtfully selected content, which is clearly reflected in its performance ranking on the OpenLLM Leaderboard. Furthermore, it features an architecture optimized for rapid inference, utilizing advanced technologies such as FlashAttention and multiquery strategies. In addition, the flexibility offered by the Apache 2.0 license allows users to pursue commercial ventures without worrying about royalties or stringent constraints. This unique blend of high performance and operational freedom positions Falcon-7B as an excellent option for developers in search of sophisticated modeling capabilities. Ultimately, the model's design and resourcefulness make it a compelling choice in the rapidly evolving landscape of machine learning.

We have integrated Llama 3 into Meta AI, our smart assistant that transforms the way people perform tasks, innovate, and interact with technology. By leveraging Meta AI for coding and troubleshooting, users can directly experience the power of Llama 3. Whether you are developing agents or other AI-based solutions, Llama 3, which is offered in both 8B and 70B variants, delivers the essential features and adaptability needed to turn your concepts into reality. In conjunction with the launch of Llama 3, we have updated our Responsible Use Guide (RUG) to provide comprehensive recommendations on the ethical development of large language models. Our approach focuses on enhancing trust and safety measures, including the introduction of Llama Guard 2, which aligns with the newly established taxonomy from MLCommons and expands its coverage to include a broader range of safety categories, alongside code shield and Cybersec Eval 2. Moreover, these improvements are designed to promote a safer and more responsible application of AI technologies across different fields, ensuring that users can confidently harness these innovations. The commitment to ethical standards reflects our dedication to fostering a secure and trustworthy AI environment.

We are excited to unveil an open-source AI model that offers the ability to be fine-tuned, distilled, and deployed across a wide range of platforms. Our latest instruction-tuned model is available in three different sizes: 8B, 70B, and 405B, allowing you to select an option that best fits your unique needs. The open ecosystem we provide accelerates your development journey with a variety of customized product offerings tailored to meet your specific project requirements. You can choose between real-time inference and batch inference services, depending on what your project requires, giving you added flexibility to optimize performance. Furthermore, downloading model weights can significantly enhance cost efficiency per token while you fine-tune the model for your application. To further improve performance, you can leverage synthetic data and seamlessly deploy your solutions either on-premises or in the cloud. By taking advantage of Llama system components, you can also expand the model's capabilities through the use of zero-shot tools and retrieval-augmented generation (RAG), promoting more agentic behaviors in your applications. Utilizing the extensive 405B high-quality data enables you to fine-tune specialized models that cater specifically to various use cases, ensuring that your applications function at their best. In conclusion, this empowers developers to craft innovative solutions that not only meet efficiency standards but also drive effectiveness in their respective domains, leading to a significant impact on the technology landscape.

The newest version of the open-source AI framework, which can be customized and utilized across different platforms, is available in several configurations: 1B, 3B, 11B, and 90B, while still offering the option to use Llama 3.1. Llama 3.2 includes a selection of large language models (LLMs) that are pretrained and fine-tuned specifically for multilingual text processing in 1B and 3B sizes, whereas the 11B and 90B models support both text and image inputs, generating text outputs. This latest release empowers users to build highly effective applications that cater to specific requirements. For applications running directly on devices, such as summarizing conversations or managing calendars, the 1B or 3B models are excellent selections. On the other hand, the 11B and 90B models are particularly suited for tasks involving images, allowing users to manipulate existing pictures or glean further insights from images in their surroundings. Ultimately, this broad spectrum of models opens the door for developers to experiment with creative applications across a wide array of fields, enhancing the potential for innovation and impact.

The latest iteration in the Llama series, Llama 3.3, marks a notable leap forward in the realm of language models, designed to improve AI's abilities in both understanding and communication. It features enhanced contextual reasoning, more refined language generation, and state-of-the-art fine-tuning capabilities that yield remarkably accurate, human-like responses for a wide array of applications. This version benefits from a broader training dataset, advanced algorithms that allow for deeper comprehension, and reduced biases when compared to its predecessors. Llama 3.3 excels in various domains such as natural language understanding, creative writing, technical writing, and multilingual conversations, making it an invaluable tool for businesses, developers, and researchers. Furthermore, its modular design lends itself to adaptable deployment across specific sectors, ensuring consistent performance and flexibility even in expansive applications. With these significant improvements, Llama 3.3 is set to transform the benchmarks for AI language models and inspire further innovations in the field. It is an exciting time for AI development as this new version opens doors to novel possibilities in human-computer interaction.

SmolLM2 features a sophisticated range of compact language models designed for effective on-device operations. This assortment includes models with various parameter counts, such as a substantial 1.7 billion, alongside more efficient iterations at 360 million and 135 million parameters, which guarantees optimal functionality on devices with limited resources. The models are particularly adept at text generation and have been fine-tuned for scenarios that demand quick responses and low latency, ensuring they deliver exceptional results in diverse applications, including content creation, programming assistance, and understanding natural language. The adaptability of SmolLM2 makes it a prime choice for developers who wish to embed powerful AI functionalities into mobile devices, edge computing platforms, and other environments where resource availability is restricted. Its thoughtful design exemplifies a dedication to achieving a balance between high performance and user accessibility, thus broadening the reach of advanced AI technologies. Furthermore, the ongoing development of such models signals a promising future for AI integration in everyday technology.

Gemma 3, introduced by Google, is a state-of-the-art AI model built on the Gemini 2.0 architecture, specifically engineered to provide enhanced efficiency and flexibility. This groundbreaking model is capable of functioning effectively on either a single GPU or TPU, which broadens access for a wide array of developers and researchers. By prioritizing improvements in natural language understanding, generation, and various AI capabilities, Gemma 3 aims to advance the performance of artificial intelligence systems significantly. With its scalable and durable design, Gemma 3 seeks to drive the progression of AI technologies across multiple fields and applications, ultimately holding the potential to revolutionize the technology landscape. As such, it stands as a pivotal development in the continuous integration of AI into everyday life and industry practices.

Llama 4 Scout represents a leap forward in multimodal AI, featuring 17 billion active parameters and a groundbreaking 10 million token context length. With its ability to integrate both text and image data, Llama 4 Scout excels at tasks like multi-document summarization, complex reasoning, and image grounding. It delivers superior performance across various benchmarks and is particularly effective in applications requiring both language and visual comprehension. Scout's efficiency and advanced capabilities make it an ideal solution for developers and businesses looking for a versatile and powerful model to enhance their AI-driven projects.

GLM-4.5V-Flash is an open-source vision-language model designed to seamlessly integrate powerful multimodal capabilities into a streamlined and deployable format. This versatile model supports a variety of input types including images, videos, documents, and graphical user interfaces, enabling it to perform numerous functions such as scene comprehension, chart and document analysis, screen reading, and image evaluation. Unlike larger models, GLM-4.5V-Flash boasts a smaller size yet retains crucial features typical of visual language models, including visual reasoning, video analysis, GUI task management, and intricate document parsing. Its application within "GUI agent" frameworks allows the model to analyze screenshots or desktop captures, recognize icons or UI elements, and facilitate both automated desktop and web activities. Although it may not reach the performance levels of the most extensive models, GLM-4.5V-Flash offers remarkable adaptability for real-world multimodal tasks where efficiency, lower resource demands, and broad modality support are vital. Ultimately, its innovative design empowers users to leverage sophisticated capabilities while ensuring optimal speed and easy access for various applications. This combination makes it an appealing choice for developers seeking to implement multimodal solutions without the overhead of larger systems.

Mistral Small 4 is a powerful open-source AI model introduced by Mistral AI to deliver advanced reasoning, multimodal understanding, and coding capabilities in a single system. The model represents the latest evolution in the Mistral Small family and consolidates multiple specialized AI technologies into one unified architecture. It integrates the reasoning capabilities of Magistral, the multimodal functionality of Pixtral, and the coding intelligence of Devstral. This design allows the model to handle tasks ranging from conversational assistance and research analysis to software development and visual data processing. Mistral Small 4 supports both text and image inputs, enabling applications such as document parsing, visual analysis, and interactive AI systems. Its mixture-of-experts architecture includes 128 experts with a small subset activated per token, allowing efficient resource usage while maintaining strong performance. The model also introduces a configurable reasoning effort parameter that allows developers to control the balance between speed and analytical depth. A large 256k context window enables it to process lengthy conversations, documents, and complex reasoning workflows. Performance optimizations significantly reduce latency and increase throughput compared with previous versions of the model. The system is designed for deployment across various environments, including cloud infrastructure, enterprise systems, and research environments. Developers can access the model through platforms such as Hugging Face, Transformers, and optimized inference frameworks. Released under the Apache 2.0 open-source license, Mistral Small 4 allows organizations to customize, fine-tune, and deploy AI solutions tailored to their specific needs. By combining reasoning, multimodal processing, and coding intelligence in one model, Mistral Small 4 simplifies AI integration for modern applications.

We are excited to unveil the latest version of our open-source large language model, which includes model weights and initial code for the pretrained and fine-tuned Llama language models, ranging from 7 billion to 70 billion parameters. The Llama 2 pretrained models have been crafted using a remarkable 2 trillion tokens and boast double the context length compared to the first iteration, Llama 1. Additionally, the fine-tuned models have been refined through the insights gained from over 1 million human annotations. Llama 2 showcases outstanding performance compared to various other open-source language models across a wide array of external benchmarks, particularly excelling in reasoning, coding abilities, proficiency, and knowledge assessments. For its training, Llama 2 leveraged publicly available online data sources, while the fine-tuned variant, Llama-2-chat, integrates publicly accessible instruction datasets alongside the extensive human annotations mentioned earlier. Our project is backed by a robust coalition of global stakeholders who are passionate about our open approach to AI, including companies that have offered valuable early feedback and are eager to collaborate with us on Llama 2. The enthusiasm surrounding Llama 2 not only highlights its advancements but also marks a significant transformation in the collaborative development and application of AI technologies. This collective effort underscores the potential for innovation that can emerge when the community comes together to share resources and insights.

Code Llama is a sophisticated language model engineered to produce code from text prompts, setting itself apart as a premier choice among publicly available models for coding applications. This groundbreaking model not only enhances productivity for seasoned developers but also supports newcomers in tackling the complexities of learning programming. Its adaptability allows Code Llama to serve as both an effective productivity tool and a pedagogical resource, enabling programmers to develop more efficient and well-documented software. Furthermore, users can generate code alongside natural language explanations by inputting either format, which contributes to its flexibility for various programming tasks. Offered for free for both research and commercial use, Code Llama is based on the Llama 2 architecture and is available in three specific versions: the core Code Llama model, Code Llama - Python designed exclusively for Python development, and Code Llama - Instruct, which is fine-tuned to understand and execute natural language commands accurately. As a result, Code Llama stands out not just for its technical capabilities but also for its accessibility and relevance to diverse coding scenarios.

Meet Gemma 3n, our state-of-the-art open multimodal model engineered for exceptional performance and efficiency on devices. Emphasizing responsive and low-footprint local inference, Gemma 3n sets the stage for a new era of intelligent applications that can be deployed while on the go. It possesses the ability to interpret and react to a combination of images and text, with upcoming plans to add video and audio capabilities shortly. This allows developers to build smart, interactive functionalities that uphold user privacy and operate smoothly without relying on an internet connection. The model features a mobile-centric design that significantly reduces memory consumption. Jointly developed by Google's mobile hardware teams and industry specialists, it maintains a 4B active memory footprint while providing the option to create submodels for enhanced quality and reduced latency. Furthermore, Gemma 3n is our first open model constructed on this groundbreaking shared architecture, allowing developers to begin experimenting with this sophisticated technology today in its initial preview. As the landscape of technology continues to evolve, we foresee an array of innovative applications emerging from this powerful framework, further expanding its potential in various domains. The future looks promising as more features and enhancements are anticipated to enrich the user experience.

Gemma encompasses a series of innovative, lightweight open models inspired by the foundational research and technology that drive the Gemini models. Developed by Google DeepMind in collaboration with various teams at Google, the term "gemma" derives from Latin, meaning "precious stone." Alongside the release of our model weights, we are also providing resources designed to foster developer creativity, promote collaboration, and uphold ethical standards in the use of Gemma models. Sharing essential technical and infrastructural components with Gemini, our leading AI model available today, the 2B and 7B versions of Gemma demonstrate exceptional performance in their weight classes relative to other open models. Notably, these models are capable of running seamlessly on a developer's laptop or desktop, showcasing their adaptability. Moreover, Gemma has proven to not only surpass much larger models on key performance benchmarks but also adhere to our rigorous standards for producing safe and responsible outputs, thereby serving as an invaluable tool for developers seeking to leverage advanced AI capabilities. As such, Gemma represents a significant advancement in accessible AI technology.

The Gemma family is composed of advanced and lightweight models that are built upon the same groundbreaking research and technology as the Gemini line. These state-of-the-art models come with powerful security features that foster responsible and trustworthy AI usage, a result of meticulously selected data sets and comprehensive refinements. Remarkably, the Gemma models perform exceptionally well in their varied sizes—2B, 7B, 9B, and 27B—frequently surpassing the capabilities of some larger open models. With the launch of Keras 3.0, users benefit from seamless integration with JAX, TensorFlow, and PyTorch, allowing for adaptable framework choices tailored to specific tasks. Optimized for peak performance and exceptional efficiency, Gemma 2 in particular is designed for swift inference on a wide range of hardware platforms. Moreover, the Gemma family encompasses a variety of models tailored to meet different use cases, ensuring effective adaptation to user needs. These lightweight language models are equipped with a decoder and have undergone training on a broad spectrum of textual data, programming code, and mathematical concepts, which significantly boosts their versatility and utility across numerous applications. This diverse approach not only enhances their performance but also positions them as a valuable resource for developers and researchers alike.

Jamba has emerged as the leading long context model, specifically crafted for builders and tailored to meet enterprise requirements. It outperforms other prominent models of similar scale with its exceptional latency and features a groundbreaking 256k context window, the largest available. Utilizing the innovative Mamba-Transformer MoE architecture, Jamba prioritizes cost efficiency and operational effectiveness. Among its out-of-the-box features are function calls, JSON mode output, document objects, and citation mode, all aimed at improving the overall user experience. The Jamba 1.5 models excel in performance across their expansive context window and consistently achieve top-tier scores on various quality assessment metrics. Enterprises can take advantage of secure deployment options customized to their specific needs, which facilitates seamless integration with existing systems. Furthermore, Jamba is readily accessible via our robust SaaS platform, and deployment options also include collaboration with strategic partners, providing users with added flexibility. For organizations that require specialized solutions, we offer dedicated management and ongoing pre-training services, ensuring that each client can make the most of Jamba’s capabilities. This level of adaptability and support positions Jamba as a premier choice for enterprises in search of innovative and effective solutions for their needs. Additionally, Jamba's commitment to continuous improvement ensures that it remains at the forefront of technological advancements, further solidifying its reputation as a trusted partner for businesses.

Amazon Nova signifies a groundbreaking advancement in foundation models (FMs), delivering sophisticated intelligence and exceptional price-performance ratios, exclusively accessible through Amazon Bedrock. The series features Amazon Nova Micro, Amazon Nova Lite, and Amazon Nova Pro, each tailored to process text, image, or video inputs and generate text outputs, addressing varying demands for capability, precision, speed, and operational expenses. Amazon Nova Micro is a model centered on text, excelling in delivering quick responses at an incredibly low price point. On the other hand, Amazon Nova Lite is a cost-effective multimodal model celebrated for its rapid handling of image, video, and text inputs. Lastly, Amazon Nova Pro distinguishes itself as a powerful multimodal model that provides the best combination of accuracy, speed, and affordability for a wide range of applications, making it particularly suitable for tasks like video summarization, answering queries, and solving mathematical problems, among others. These innovative models empower users to choose the most suitable option for their unique needs while experiencing unparalleled performance levels in their respective tasks. This flexibility ensures that whether for simple text analysis or complex multimodal interactions, there is an Amazon Nova model tailored to meet every user's specific requirements.

Llama, a leading-edge foundational large language model developed by Meta AI, is designed to assist researchers in expanding the frontiers of artificial intelligence research. By offering streamlined yet powerful models like Llama, even those with limited resources can access advanced tools, thereby enhancing inclusivity in this fast-paced and ever-evolving field. The development of more compact foundational models, such as Llama, proves beneficial in the realm of large language models since they require considerably less computational power and resources, which allows for the exploration of novel approaches, validation of existing studies, and examination of potential new applications. These models harness vast amounts of unlabeled data, rendering them particularly effective for fine-tuning across diverse tasks. We are introducing Llama in various sizes, including 7B, 13B, 33B, and 65B parameters, each supported by a comprehensive model card that details our development methodology while maintaining our dedication to Responsible AI practices. By providing these resources, we seek to empower a wider array of researchers to actively participate in and drive forward the developments in the field of AI. Ultimately, our goal is to foster an environment where innovation thrives and collaboration flourishes.