Hugging Face

DeepSeek-R1 is DeepSeek's open-weight reasoning model, a 671B mixture-of-experts with 37B active parameters and a 131,072-token context. It is trained with large-scale reinforcement learning and released under the MIT license. It targets math, code and reasoning.

DeepSeek V3.1 Terminus is an open-weight update to DeepSeek V3.1. It keeps the original capabilities while addressing user reports on language consistency and agent capabilities. It supports reasoning, streaming and function calling.

DeepSeek V3.1 is an open-weight hybrid reasoning model from DeepSeek with a 131,072-token context window, strong coding and agentic tool-use performance. Served free through SambaNova Cloud's fast RDU inference and SiliconFlow.

DeepSeek-V3 is DeepSeek's 671B mixture-of-experts general-purpose model. It handles multilingual, coding and reasoning tasks. It is a text model with streaming and function calling.

DeepSeek-V4-Flash is DeepSeek's open-weight fast mixture-of-experts model for high-throughput chat and coding. It accepts text and image input and returns text. It supports reasoning, tool calling and agentic use.

DeepSeek V4 Pro is DeepSeek's open-weight high-capability reasoning model. It is a text model for chat and coding with streaming and function calling.

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash. It is an open-weight sparse mixture-of-experts model with native vision input, text output and a 1M-token context window.

DeepSeek V4.1 Flash is the open-weight, cost-efficient sparse mixture-of-experts tier of the V4.1 family. It has 552B total parameters with 8B active on input and 16B on output, 1M context, and native vision in with text out. This is the original September 2026 checkpoint.

Gemma 3 4B IT is Google's instruction-tuned 4B open model with text and image input. It has a 128K context window and multilingual support in over 140 languages. It supports tool calling.

Gemma 4 26B A4B is an open-weight model from Google's Gemma 4 family, built from Gemini 3 research to maximize intelligence per parameter. It takes text and image input and generates text. It supports reasoning, tool calling, and coding.

Gemma 4 31B is Google's open-weight dense open reasoning model for complex reasoning, agentic workflows, coding, and multimodal understanding. It takes text and image input and generates text. It supports tool calling and a thinking mode.

Granite 4.2 30B is IBM's flagship dense 30B reasoning model, released as open-weight under Apache-2.0. It has built-in chain-of-thought with full, low-effort and non-thinking modes, plus reasoning-augmented tool calling. Context window is 131,072 tokens.

Granite 4.2 8B is the open-weight, mid-size dense reasoning model in IBM's Granite 4.2 family. It offers full, low-effort and non-thinking modes plus tool calling. Context window is 131,072 tokens, with up to 117,964 output tokens.

Ling-3.0-flash-Fin is inclusionAI's open-weight finance-focused mixture-of-experts model, built on Ling-3.0-flash with 124B total and 5.1B active parameters. It targets investment research, market analysis and financial reasoning. It keeps general reasoning and coding skills.

Ling-3.0-flash-VL is inclusionAI's open-weight native multimodal mixture-of-experts model with 124B parameters and about 5.5B active per token. It adds image and video understanding. It suits visual reasoning, document and chart reading, and agentic GUI tasks.

Ling-3.0-flash is inclusionAI's open-weight instruct mixture-of-experts model with 124B parameters and about 5.1B active per token. It is built for token efficiency and production-scale agentic inference. It suits coding, document processing and lightweight agent workflows.

Llama 3.1 8B Instruct is Meta's compact instruction-tuned model, optimized for fast inference and edge deployments. It supports chat, reasoning, coding, function calling, and streaming, with text in and text out.

Llama 3.3 70B Instruct is Meta's open-weight instruction-tuned model with 70B parameters and a 131072-token context window. It is tuned for multilingual dialogue, with tool use on par with Llama 3.1 70B. It suits chat, reasoning, and coding.

Llama 4 Scout 17B 16E is Meta's open-weight multimodal mixture-of-experts model with 17B active and 109B total parameters. It takes text and image input and has a 10M-token input context. It fits on a single H100 GPU.

Llama Guard 4 12B is Meta's natively multimodal safety classifier with 12B parameters. It labels LLM prompts and responses as safe or unsafe and lists violated categories from the MLCommons hazards taxonomy. Text and image go in, text comes out.

Phi 4 is Microsoft Research's open-weight model for complex reasoning that also runs efficiently with limited memory or when quick responses are needed. It has a 16,384-token context window and takes text in and gives text out.

MiniMax M2.5 is MiniMax's large language model for real-world productivity. It extends M2.1 coding expertise into office work such as generating Word, Excel and PowerPoint files. It scores 80.2% on SWE-Bench Verified and 76.3% on BrowseComp.

MiniMax M2.7 is MiniMax's large language model for complex software engineering, agentic tool use and office productivity workflows. It supports complex agent harnesses, dynamic tool search and Agent Teams. It takes text and supports function calling.

MiniMax M3 is MiniMax's multimodal language model for coding and agentic work. It accepts text, image and video input and returns text. It supports reasoning, function calling, structured output and multilingual use.

MiniMax M3.1 Flash is MiniMax's open-weight multimodal model for complex agentic tasks, coding and cybersecurity. It accepts text, image and video input and has a 1M-token context window. It always thinks, with adjustable effort, and its weights are not yet released.

Kimi K2.5 is Moonshot AI's open-weight mixture-of-experts model with native vision, tool calling and structured outputs. It has 1T total and 32B active parameters, a 256K context window and a Modified MIT license.

Kimi K2.6 is Moonshot AI's open-weight large mixture-of-experts model with agentic tool use, vision input and long-context memory. It supports reasoning and streaming, and takes text and image input.

Kimi K2.7 Code is Moonshot AI's open-weight coding-focused model for end-to-end programming tasks over long contexts. It is a native multimodal mixture-of-experts model with 32B active of roughly 1T total parameters and always-on thinking.

Kimi K3.1 Pro is the first model in Moonshot AI's open-weight K3.1 series, a post-trained version of Kimi K3. It has a 1M-token context window and native visual understanding, and improves on K3 in coding, 3D and CAD modeling and financial research. Thinking is always on.

Kimi K3 is Moonshot AI's open-weight multimodal reasoning model with native visual understanding. It accepts text, image and video input for long-horizon software engineering, knowledge work and CAD. Thinking is always on.

GPT-OSS-120b is OpenAI's open-weight mixture-of-experts reasoning model under the Apache-2.0 license. It has 116.8B total and 5.1B active parameters and a 131,072-token context window. It supports function calling and runs on one 80 GB GPU with MXFP4 weights.

GPT-OSS 20B is OpenAI's open-weight reasoning model for agentic tasks and low-latency edge use, under Apache-2.0. It is a mixture-of-experts model with 20.9B total and 3.6B active parameters and a 131,072-token context. It runs within 16 GB of memory with MXFP4 weights.

GPT-OSS Safeguard 20B is OpenAI's open-weight safety reasoning model built on gpt-oss-20b (Apache 2.0). It is a 21B-parameter MoE tuned for content classification, input and output filtering, and trust and safety judgments with reasoning traces.

Qwen2.5-72B-Instruct is Alibaba Qwen's open-weight 72.7B-parameter general chat model. It is stronger at coding and maths than Qwen2, supports 29+ languages and handles function calling.

Qwen 2.5 Coder 32B is Alibaba's open-weight specialized coding model with 32B parameters. It targets code generation, completion and debugging across 92 programming languages, with function calling and streaming.

Qwen2.5 VL 72B Instruct is Qwen's open-weight 72B vision-language model. It takes text and images and answers in text, and reads charts, icons, graphics and page layouts.

Qwen3-14B is an open-weight 14.8B-parameter dense model from Alibaba Qwen that balances quality and latency. It supports reasoning, function calling, 100+ languages and dialects, instruction following and translation.

Qwen3 235B A22B Thinking 2507 is Qwen's open-weight Mixture-of-Experts model tuned for complex reasoning, with a 128,000-token context window. It supports function calling and streaming, and takes text in and returns text out.

Qwen3-8B is Alibaba Qwen's open-weight small dense model with 8B parameters. It is fast and efficient, supports reasoning, and suits lightweight chat and tool use.

Qwen3 Next 80B A3B Instruct is an open-weight, instruction-tuned chat model in Qwen's Qwen3-Next series, built for fast, stable responses without thinking traces. It has a 262,144-token context window and supports function calling and streaming.

Qwen3 VL 235B A22B Instruct is Qwen's open-weight multimodal model that combines text generation with visual understanding of images and video. It has a 262,144-token context window and supports function calling.

Qwen3 VL 30B A3B Instruct is Qwen's open-weight multimodal model that combines text generation with visual understanding of images and videos. It targets instruction following and supports function calling.

Qwen3.5-122B-A10B is Qwen's open-weight native vision-language model with a hybrid architecture. It combines linear attention with a sparse mixture-of-experts, takes text, image and video input.

Qwen3.5-27B is Alibaba's largest open-weight dense Qwen3.5 model. It has a thinking mode, tool calling, multi-token prediction and 201 languages, with text, image and video input.

Qwen3.5-35B-A3B is Qwen's open-weight native vision-language model with a hybrid of linear attention and a sparse mixture-of-experts. It takes text, image and video input, has a 262,144-token context window and supports reasoning.

Qwen 3.5 397B A17B is Alibaba's open-weight mixture-of-experts model with 397B total and 17B active parameters. It supports reasoning and function calling, and takes text, image and video input.

Qwen3.5-9B is an open-weight model from Alibaba's Qwen3.5 series with a hybrid Gated Delta Networks and sparse MoE architecture. It has a thinking mode, tool calling and 201 languages.

Qwen3.8 2.4T A95B is Qwen's sparse mixture-of-experts model, the open-weight variant of Qwen3.8 Max. It has 95 billion active of 2.4 trillion total parameters.

Qwen3.8-27B is Alibaba's open-weight dense Qwen3.8 model for agentic coding and complex reasoning, with a native thinking mode. It targets multi-step agent work and large coding tasks.

Beam 1.0 is Reflection's open-weights mixture-of-experts model with 501B total and 23B active parameters. It is built for token-efficient reasoning, agentic tool use, and software engineering. Weights are Apache-2.0.

Step 3.5 Flash is StepFun's open-weight sparse Mixture-of-Experts model with 196.81B total parameters and about 11B active per token. It uses a 45-layer transformer with 288 routed experts, Top-8 selection, and 256K context for reasoning and agentic tasks.

Step 3.7 Flash is StepFun's open-weight 1T parameter multimodal Mixture-of-Experts model for long-horizon coding, agentic tool use, and image and video understanding. It takes text and image input and supports structured output.

Hy4 Preview is Tencent Hunyuan's open-weight 770B mixture-of-experts model with 49B active parameters, built for agents and coding. It targets office automation and complex tool use.

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab. It has 12B active parameters out of 276B total. It takes text, image, and audio input and returns text.

Inkling is Thinking Machines Lab's first open-weights foundation model. It is a 975B-parameter multimodal mixture-of-experts transformer with 41B active. It takes text, image, and audio input, with switchable reasoning effort and tool use.

MiMo V2.5 Pro is Xiaomi's open-weight flagship model for agentic work, complex software engineering, and long-horizon tasks. It accepts text, image and video input. It completes professional tasks involving thousands of tool calls.

MiMo V2.5 is Xiaomi's open-weight native omnimodal model with Pro-level agentic performance. It accepts text, image and video input, improves on MiMo V2 Omni in multimodal perception, and suits agent frameworks.

GLM 4.5 Air is the open-weight, lightweight variant of Z.ai's GLM-4.5 flagship family, built for agent-centric applications. It supports reasoning, function calling, and streaming, with a 131,072-token context window.

GLM-4.5 is Z-AI's open-weight foundational model for agent-oriented applications. It is a mixture-of-experts model with 355B total and 32B active parameters, trained on 15 trillion tokens. It has a 128K context window, hybrid thinking modes, and strong tool use and coding.

GLM 4.5V is Z.ai's open-weight vision-language foundation model for multimodal agent applications. It takes text and image input and returns text, with reasoning and function calling. The context window is 65,536 tokens.

GLM-4.6 is Z-AI's open-weight mixture-of-experts model with 355B total and 32B active parameters, under the MIT license. It has a 200K context window, up from 128K, and a 128K max output. It improves coding, tool use, and search-based agents.

GLM-4.6V is the vision open-weight variant of Z-AI's GLM-4.6 model. It takes text and image input. It suits document intelligence, code-screenshot interpretation, and multimodal reasoning.

GLM-4.7 Flash is an open-weight fast multilingual text generation model from Z-AI with a 131,072 token context window. It is optimized for dialogue, instruction following, and multi-turn tool calling across 100+ languages.

GLM-4.7 is Z-AI's open-weight multilingual text generation model with a 131,072 token context window. It supports chat, instruction following, multi-turn tool calling, and reasoning across 100+ languages.

GLM-5.1 is Z-AI's open-weight flagship foundation model for long-horizon autonomous tasks. It has a 128K output window and scores 58.4 on SWE-Bench Pro. It supports thinking mode, function calling, and MCP integration.

GLM-5.2 is Z-AI's open-weight flagship reasoning model with a 128K output window. It supports controllable thinking effort, function calling, and MCP integration. It targets long-horizon autonomous coding and agentic tasks.

GLM-5.3 is Z.AI's open-weight reasoning model for coding and agentic workflows. It targets complex software engineering, long-running agents, and vulnerability analysis. It uses the same base model as GLM-5.2 with scaled post-training for stronger coding and token efficiency.

GLM-5 is Z-AI's open-weight general-purpose foundation model for reasoning, coding, and agentic workloads. It has a 128K context window and 32K output. It supports thinking mode, function calling, and structured outputs.