AI Agent Hub

LLM Models

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

1,113 models for "Chat" Compare
🤖
Step-3.5-Flash-FP8
stepfun-ai

Step 3.5 Flash (visit website) is our most capable open-source foundation model, engineered to deliver frontier reasoning and agentic capabilities with exceptional efficiency. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B p…

Open Source ↓ 1.5K
🤖
Intern-S2-Mobius
internlm

💻Github Repo • 🤗Model Collections • 🌳Arch Space

Open Source ↓ 1.5K
🤖
glm-4-9b-chat-1m-hf
zai-org

If you are using the weights from this repository, please update to

Open Source 9.0B ↓ 1.5K
🤖
InternVL3_5-14B-Instruct
OpenGVLab

[\[📂 GitHub\]](https://github.com/OpenGVLab/InternVL) [\[📜 InternVL 1.0\]](https://huggingface.co/papers/2312.14238) [\[📜 InternVL 1.5\]](https://huggingface.co/papers/2404.16821) [\[📜 InternVL 2.5\]](https://huggingface.co/papers/2412.05271) [\[📜 InternVL2.5-MPO\]](https://huggi…

Multimodal 14.0B ↓ 1.5K
🤖
Llama-SEA-LION-v3.5-8B-R
aisingapore

SEA-LION is a collection of Large Language Models (LLMs) which have been pretrained and instruct-tuned for the Southeast Asia (SEA) region.

Open Source 8.0B ↓ 1.5K
🤖
ERNIE-4.5-0.3B-Base-PT
baidu

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

Open Source 0.3B ↓ 1.5K
🤖
internlm2-chat-20b-4bits
internlm

INT4 Weight-only Quantization and Deployment (W4A16)

Open Source 20.0B ↓ 1.4K
🤖
InternVL2_5-8B-MPO
OpenGVLab

[\[📂 GitHub\]](https://github.com/OpenGVLab/InternVL) [\[📜 InternVL 1.0\]](https://huggingface.co/papers/2312.14238) [\[📜 InternVL 1.5\]](https://huggingface.co/papers/2404.16821) [\[📜 InternVL 2.5\]](https://huggingface.co/papers/2412.05271) [\[📜 InternVL2.5-MPO\]](https://huggi…

Multimodal 8.0B ↓ 1.4K
🤖
glm-edge-v-2b
zai-org

Install the transformers library from the source code:

Open Source 2.0B ↓ 1.4K
🤖
internlm-xcomposer2-vl-7b-4bit
internlm

InternLM-XComposer2 is a vision-language large model (VLLM) based on InternLM2 for advanced text-image comprehension and composition.

Multimodal 7.0B ↓ 1.4K
🤖
InternVL3-1B-Instruct
OpenGVLab

[\[📂 GitHub\]](https://github.com/OpenGVLab/InternVL) [\[📜 InternVL 1.0\]](https://huggingface.co/papers/2312.14238) [\[📜 InternVL 1.5\]](https://huggingface.co/papers/2404.16821) [\[📜 InternVL 2.5\]](https://huggingface.co/papers/2412.05271) [\[📜 InternVL2.5-MPO\]](https://huggi…

Multimodal 1.0B ↓ 1.3K
🤖
AI21-Jamba2-Mini
ai21labs

Jamba2 Mini is an open source small language model built for enterprise reliability. With 12B active parameters (52B total), it delivers precise question answering without the computational overhead of reasoning models. The model's SSM-Transformer architecture provides a memory-e…

Open Source ↓ 1.3K