AI Agent Hub

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
351 models for "DPO" Compare
EXAONE-4.0-32B-FP8 logo
EXAONE-4.0-32B-FP8
LGAI-EXAONE

🎉 License Updated! We are pleased to announce our more flexible licensing terms 🤗 ✈️ Try on FriendliAI (licensed under commercial purposes) 📢 EXAONE 4.0 is officially supported by HuggingFace transformers! Please check out the guide below

Reasoning 32.0B ★ 8.0 ↓ 9.1K
EXAONE-4.0.1-32B logo
EXAONE-4.0.1-32B
LGAI-EXAONE

✈️ Try on FriendliAI (licensed under commercial purposes) 📢 EXAONE 4.0 is officially supported by HuggingFace transformers! Please check out the guide below

Reasoning 32.0B ★ 8.0 ↓ 4K
ERNIE-4.5-300B-A47B-PT logo
ERNIE-4.5-300B-A47B-PT
baidu

[!NOTE] Note: " -Paddle " models use PaddlePaddle weights, while " -PT " models use Transformer-style PyTorch weights.

Open Source 300.0B ★ 8.0 ↓ 2.8K
EXAONE-4.0-32B-AWQ logo
EXAONE-4.0-32B-AWQ
LGAI-EXAONE

🎉 License Updated! We are pleased to announce our more flexible licensing terms 🤗 ✈️ Try on FriendliAI (licensed under commercial purposes) 📢 EXAONE 4.0 is officially supported by HuggingFace transformers! Please check out the guide below

Open Source 32.0B ★ 8.0 ↓ 1K
Step3-VL-10B-FP8 logo
Step3-VL-10B-FP8
stepfun-ai

- 🚀 Online Demo : Explore Step3-VL-10B on Hugging Face Spaces ! - 📢 [Notice] FP8 Quantization Support : FP8 quantized weights are now available. (Download link) - 📢 [Notice] vLLM Support: vLLM integration is now officially supported! (PR 32329) - ✅ [Fixed] HF Inference: Resolved…

Multimodal 10.0B ★ 8.0 ↓ 825
ERNIE-4.5-300B-A47B-Paddle logo
ERNIE-4.5-300B-A47B-Paddle
baidu

[!NOTE] Note: " -Paddle " models use PaddlePaddle weights, while " -PT " models use Transformer-style PyTorch weights.

Open Source 300.0B ★ 8.0 ↓ 472
ERNIE-4.5-300B-A47B-Base-PT logo
ERNIE-4.5-300B-A47B-Base-PT
baidu

[!NOTE] Note: " -Paddle " models use PaddlePaddle weights, while " -PT " models use Transformer-style PyTorch weights.

Open Source 300.0B ★ 8.0 ↓ 398
ERNIE-4.5-300B-A47B-2Bits-Paddle logo
ERNIE-4.5-300B-A47B-2Bits-Paddle
baidu

The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:

Open Source 300.0B ★ 8.0 ↓ 199
ERNIE-4.5-300B-A47B-Base-Paddle logo
ERNIE-4.5-300B-A47B-Base-Paddle
baidu

[!NOTE] Note: " -Paddle " models use PaddlePaddle weights, while " -PT " models use Transformer-style PyTorch weights.

Open Source 300.0B ★ 8.0 ↓ 177
EXAONE-4.0-32B-GPTQ logo
EXAONE-4.0-32B-GPTQ
LGAI-EXAONE

🎉 License Updated! We are pleased to announce our more flexible licensing terms 🤗 ✈️ Try on FriendliAI (licensed under commercial purposes) 📢 EXAONE 4.0 is officially supported by HuggingFace transformers! Please check out the guide below

Open Source 32.0B ★ 8.0 ↓ 155
ERNIE-4.5-300B-A47B-W4A8C8-TP4-Paddle logo
ERNIE-4.5-300B-A47B-W4A8C8-TP4-Paddle
baidu

[!NOTE] Note: " -Paddle " models use PaddlePaddle weights, while " -PT " models use Transformer-style PyTorch weights.

Open Source 300.0B ★ 8.0 ↓ 144
ERNIE-4.5-300B-A47B-FP8-Paddle logo
ERNIE-4.5-300B-A47B-FP8-Paddle
baidu

[!NOTE] Note: " -Paddle " models use PaddlePaddle weights, while " -PT " models use Transformer-style PyTorch weights.

Open Source 300.0B ★ 8.0 ↓ 139