Best Open-Weight LLMs to Run Locally
Language models you can download and run, such as Qwen3 and gpt-oss, for chat, reasoning and tool calling.
An open-weight local LLM family from Google DeepMind for phones, PCs and servers, with Ollama and LM Studio support and an Apache 2.0 JAX library.
5.8KUpdated 2 days agoApache-2.0
Android#LM Studio integration#LoRA#Multilingual
Gemma is Google DeepMind’s family of open-weight AI models for developers building applications that can run on their own hardware. Its range covers compact models for phones and IoT devices alongside larger Gemma 4 models for reasoning on personal computers and servers. Some applications can work offline, keeping model inference on the device. Google AI Studio and Google Cloud are also available for hosted use.
Edge and Embedded AIEmbedding and Reranker ModelsLLM Fine-TuningOpen-Weight LLMsVision-Language Models+0
A language model family with public weights for local CPU or GPU use through Ollama, llama.cpp, and LM Studio, plus server deployment.
27.7KUpdated 9 months ago
#Batch processing#GGUF#Hugging Face integration
Qwen3 is a family of language models from Alibaba Cloud’s Qwen team for people who want to run models locally or on their own servers. It spans smaller and larger dense models as well as mixture-of-experts models. The weights are publicly available.
Open-Weight LLMs+0
An open-source audio AI model for local transcription, translation and Q&A. Runs offline with vLLM or Transformers under Apache 2.0.
10.8KUpdated 3 months agoApache-2.0
#Hugging Face integration#Multilingual#Multimodal input
Voxtral is Mistral AI's open-source audio and text model for developers building self-hosted speech applications. It can answer questions about recordings and produce structured summaries within the same model that transcribes speech. Mistral's separate mistral-inference library is archived and no longer maintained; Voxtral supports vLLM and Hugging Face Transformers.
Open-Weight LLMsSpeech-to-Text and TranscriptionSpeech-to-Text ModelsTranslation+0
A self-hosted LLM with a 256K context window, vLLM and Transformers support, and research and commercial use under the Jamba Open Model License.
huggingface.coOpen-Weight LLMs
#Hugging Face integration#LoRA#Multilingual
Jamba is AI21's language model family for teams building AI applications on their own servers. The documented Large 1.7 model combines Mamba state-space models with Transformer attention to process long context efficiently. A 256K-token context window makes it relevant for work that depends on lengthy documents, such as investment research, due diligence and reviewing procurement responses.
Open-Weight LLMs+0
An open weights LLM you can self-host with Transformers, with document citations, tool calling and a CC-BY-NC-4.0 noncommercial license.
huggingface.coOpen-Weight LLMs
#Guardrails#Hugging Face integration#Multilingual
Command A is an open weights language model from Cohere and Cohere Labs for researchers and developers building self-hosted chatbots, document assistants and AI agents. Its focus is business tasks that combine multilingual text, supplied documents and external tools. You can run the model on your own hardware; Cohere also offers hosted chat through a playground and Hugging Face Space.
Open-Weight LLMs+0
A family of AI models you can run offline with Ollama, llama.cpp or LM Studio, with open weights and training data for building specialized agents.
2.1KUpdated 3 weeks agoApache-2.0
Linux#GGUF#Guardrails#Hugging Face integration
Nemotron is NVIDIA's family of AI models for developers building agents that reason, write code and call tools. You can run models locally for private, offline work or deploy them on your own servers. NVIDIA publishes model weights, training data and recipes so teams can inspect and adapt the models for their applications.
Datasets and Synthetic DataEmbedding and Reranker ModelsLLM Fine-TuningOpen-Weight LLMsVision-Language Models+0
LLM models for local or cloud inference, with downloadable weights and function calling. The Apache 2.0 inference library is archived.
10.8KUpdated 3 months agoApache-2.0
Docker#Hugging Face integration#Multimodal input#Tool calling
Mistral Small and Large are downloadable language models for developers building chat, reasoning and tool-using applications on their own infrastructure. Capabilities and hardware requirements depend on the release. Mistral Small 3.1 adds image understanding to text generation, while Mistral Large 2 is a larger text model.
Open-Weight LLMsVision-Language Models+0
Open-source LLM for self-hosted AI agents, with thinking and direct-response modes, MIT licensing, and support for vLLM and SGLang.
huggingface.coCoding Models
#Hugging Face integration#LoRA#Multilingual
GLM-4.5 is an open-source language model for developers building AI agents and coding tools on their own servers. It combines reasoning with tool calling and offers a choice between thinking mode for complex tasks and non-thinking mode for direct responses. The MIT license permits commercial use and modification.
Coding ModelsOpen-Weight LLMs+0
A local LLM family for chat, coding and multilingual tasks, with GGUF and Hugging Face formats for CPU or GPU use and support for llama.cpp and MLX.
127Updated 12 months ago
macOS#GGUF#Hugging Face integration#llama.cpp backend
Falcon-H1 is a family of language models from the Technology Innovation Institute for developers building local AI applications or serving models on their own hardware. Its hybrid design combines attention with Mamba2 state space models to reduce memory use and speed up inference. Model sizes cover smaller devices and larger server deployments.
Open-Weight LLMs+0
A self-hosted language model series for coding and tool use, with Base and Instruct variants and a hosted OpenAI/Anthropic-compatible API.
11.1KUpdated 11 months ago
#Hugging Face integration#Quantization#Tool calling
Kimi K2 is Moonshot AI's language model series for developers building coding assistants and AI agents, and researchers who want a foundation model to customize. You can run its checkpoints on your own infrastructure or use Moonshot's hosted API. Local inference runs on your hardware; the hosted API sends requests to Moonshot's service.
Coding ModelsOpen-Weight LLMs+0
A self-hosted language model for reasoning and agent tasks, with fast and slow thinking modes, a 256K context window, and Transformers and vLLM support.
820Updated 1 year ago
#Quantization#Tool calling
Hunyuan-A13B is Tencent's downloadable language model for developers and researchers building self-hosted AI applications. It supports general text tasks, reasoning and agent workloads, with a choice between quick responses and more deliberate reasoning. It's part of the broader Hunyuan model family, which Tencent also offers through its website.
Open-Weight LLMs+0
Language models for English, Korean and Spanish, with reasoning and tool use. Includes an on-device model and GGUF, GPTQ and AWQ formats.
107Updated 1 year ago
#GGUF#Hugging Face integration#Multilingual
EXAONE 4.0 is a family of language models from LG AI Research that combines general language tasks and complex problem solving in the same model. It's aimed at developers building multilingual AI applications, including on-device apps and agents that use tools. It supports English, Korean and Spanish.
Open-Weight LLMs+0
An open-source local LLM for reasoning and math. Run it on your own hardware without cloud connectivity, or use Microsoft's hosted inference APIs.
3.9KUpdated 1 month agoMIT
#Hugging Face integration#Ollama integration#Works offline
Phi-4 is Microsoft's small language model for complex reasoning and math problem solving. It's for developers building generative AI applications who want to run a model on their own hardware, rather than depend on a cloud connection. The original Phi-4 has 14 billion parameters and uses the MIT license; hardware needs depend on the chosen model and precision.
Open-Weight LLMs+0
An open-source AI model family for on-premises deployment, licensed under Apache 2.0, with language, speech, vision and guardrail models.
273Updated 2 years agoApache-2.0
Linux#Guardrails#Hugging Face integration#LM Studio integration
Granite is IBM's family of open-source AI models for developers and businesses that want to run and customize AI on their own hardware or servers. The language-model repository listed here is archived and no longer maintained. The broader family includes models for language, speech, document understanding and forecasting, released under Apache 2.0 for research and commercial use.
Coding ModelsEmbedding and Reranker ModelsOpen-Weight LLMsSpeech-to-Text ModelsVision-Language Models+0
A bilingual local LLM family for English and Chinese, with chat and base models, version-specific licensing, and quantized variants for consumer GPUs.
7.8KUpdated 2 years agoApache-2.0
Docker#Hugging Face integration#llama.cpp backend#Multilingual
Yi is a family of open-weight language models from 01.AI for developers, researchers, and businesses that want to run English and Chinese models on their own hardware. It includes models for conversation and base models for fine-tuning, with license terms that depend on the release. Yi-1.5 code and weights use Apache 2.0; the original Yi releases have separate community terms.
Open-Weight LLMs+0
Open-source reasoning LLM for self-hosted use through vLLM or Transformers, with million-token context and function calling under Apache 2.0.
3.2KUpdated 1 year agoApache-2.0
#Hugging Face integration#Multilingual#Tool calling
MiniMax-M1 is an open-source reasoning model for developers building agents or working on complex software and mathematical problems. Its million-token context window makes it a candidate for tasks with long inputs that also need extended reasoning. You can serve the model on your own infrastructure through vLLM or use it through Transformers.
Coding ModelsOpen-Weight LLMs+0
An open-source LLM family with reasoning and chat models, Transformers support, and a long-context variant that accepts up to one million tokens.
7.3KUpdated 1 year agoApache-2.0
#Hugging Face integration#Tool calling#Web search
InternLM is a family of downloadable language models for developers and researchers building their own AI applications. It includes models for general conversation, complex reasoning and coding, with separate base and chat variants for customization or use in an assistant.
Open-Weight LLMs+0
A language model family with downloadable weights, training data and code for people who want to run models locally or study how they're built.
6.7KUpdated 10 months agoApache-2.0
#Tool calling
OLMo is a family of language models for researchers and developers who want to inspect, adapt or run a model on their own hardware. Weights are downloadable. Ai2 also provides the training data, code, checkpoints and reports behind the models, giving researchers material to study the full training process rather than only the finished model.
Open-Weight LLMs+0
A local LLM family for developers and researchers, with downloadable weights, text and vision models, and custom licensing for research and commercial use.
7.7KUpdated 12 months ago
#Hugging Face integration#Multimodal input#Quantization
Llama is Meta's family of large language models for developers, researchers and businesses that want to run models on their own hardware or servers. Its downloadable weights let you build generative AI applications with local inference. Access requires license acceptance and approval, and the weights use custom licensing for research and commercial use.
Open-Weight LLMsVision-Language Models+0
DeepSeek-V3 and R1 are downloadable language-model families for local text generation and reasoning.
92KUpdated 1 year agoMIT
#Hugging Face integration
DeepSeek-V3 and DeepSeek-R1 are downloadable language models for developers who want to run text generation and reasoning on their own hardware. V3 is a mixture-of-experts text model. R1 builds on DeepSeek-V3-Base and focuses on reasoning tasks such as math and coding. The V3 and R1 repositories describe their respective models; the R1 repository links to downloadable weights.
Open-Weight LLMs+0
An open source 3B local LLM that runs on CPU or CUDA GPU and supports direct or reasoning responses, six languages and a 128k context window.
3.9KUpdated 1 week agoApache-2.0
#Hugging Face integration#Multilingual#Tool calling
SmolLM3 is a 3B parameter language model from Hugging Face for developers and researchers who want to run an LLM on their own hardware. It comes as a base model and an instruction-tuned model for chat, reasoning and tool calling. Both run locally.
Open-Weight LLMs+0
Open-weight local LLMs under Apache 2.0, with 20B and 120B models that work with Ollama, LM Studio and vLLM.
20.4KUpdated 2 months agoApache-2.0
macOS · Linux#Hugging Face integration#LM Studio integration#Ollama integration
gpt-oss is a pair of OpenAI reasoning models for developers who want to run a local LLM or host one on their own server. The models are open weight and licensed under Apache 2.0. OpenAI also has a hosted browser demo, separate from running the models on your hardware.
Open-Weight LLMs+0
