LLM Models

Browse the world's large language models. Compare parameters, benchmarks, VRAM and more.

✨ All 2132 🔓 Open Source 1253 🔒 Closed Source 293 👁️ Multimodal 371 💻 Code 148 🧠 Reasoning 67 Qwen 120 openai 107 OpenGVLab 78 internlm 71 nvidia 71 NousResearch 67 deepseek-ai 66 meta-llama 66 google 65 inclusionAI 62 tokyotech-llm 61 tiiuae 60

Qwen3-Coder-30B-A3B-Instruct-FP8

Qwen

Qwen3-Coder is available in multiple sizes. Today, we're excited to introduce Qwen3-Coder-30B-A3B-Instruct-FP8 . This streamlined model maintains impressive performance and efficiency, featuring the following key enhancements:

Code 30.5B ↓ 932.3K

Qwen3-Coder-30B-A3B-Instruct

Qwen

Qwen3-Coder is available in multiple sizes. Today, we're excited to introduce Qwen3-Coder-30B-A3B-Instruct . This streamlined model maintains impressive performance and efficiency, featuring the following key enhancements:

Code 30.0B ↓ 737K

Qwen3-Coder-480B-A35B-Instruct-FP8

Qwen

Today, we're announcing Qwen3-Coder , our most agentic code model to date. Qwen3-Coder is available in multiple sizes, but we're excited to introduce its most powerful variant first: Qwen3-Coder-480B-A35B-Instruct . featuring the following key enhancements:

Code 480.0B ↓ 624.9K

Qwen3-4B-Thinking-2507

Qwen

Over the past three months, we have continued to scale the thinking capability of Qwen3-4B, improving both the quality and depth of reasoning. We are pleased to introduce Qwen3-4B-Thinking-2507 , featuring the following key enhancements:

Reasoning 4.0B ↓ 603.7K

Qwen3-8B-FP8

Qwen

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities,…

Open Source 8.2B ↓ 581.3K

UI-TARS-1.5-7B

ByteDance-Seed

--- license: apache-2.0 language: - en pipeline tag: image-text-to-text tags: - multimodal - gui library name: transformers ---

Multimodal 7.0B ↓ 466K

SmolLM2-360M

HuggingFaceTB

1. Model Summary 2. Limitations 3. Training 4. License 5. Citation

Open Source ↓ 394.9K

phi-4

microsoft

------------------------- ------------------------------------------------------------------------------- Developers Microsoft Research Description phi-4 is a state-of-the-art open model built upon a blend of synthetic datasets, data from filtered public domain websites, and acqu…

Open Source ↓ 389.8K

Phi-3-mini-4k-instruct

microsoft

🎉 Phi-3.5 : [[mini-instruct]](https://huggingface.co/microsoft/Phi-3.5-mini-instruct); [[MoE-instruct]](https://huggingface.co/microsoft/Phi-3.5-MoE-instruct) ; [[vision-instruct]](https://huggingface.co/microsoft/Phi-3.5-vision-instruct)

Open Source ↓ 366.6K

Phi-3.5-mini-instruct

microsoft

🎉 Phi-4 : [multimodal-instruct onnx]; [mini-instruct onnx]

Open Source ↓ 364.5K