AI Agent Hub

LLM Models

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

1,108 models for "Chat" Compare
🤖
Qwen3.8-27B
Qwen

[!Note] This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, TokenSpeed, etc.

Open Source 27.0B ★ 52.0 ↓ 4.7M
🤖
DeepSeek-V4-Flash-0731
deepseek-ai

DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash , superseding the preview version, with substantially enhanced agentic capabilities. It has the same model structure as DeepSeek-V4-Flash-DSpark, i.e. it comes with a speculative decoding module attached.

Open Source ★ 52.0 ↓ 4.6M
🤖
DeepSeek-V4-Flash
deepseek-ai

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

Open Source ★ 52.0 ↓ 1.7M
🤖
DeepSeek-V4-Flash-DSpark
deepseek-ai

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

Open Source ★ 52.0 ↓ 381.7K
🤖
OpenAI: GPT-5.6 Luna (batch)
openai

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

Closed Source ★ 52.0
🤖
OpenAI: GPT-5.6 Luna
openai

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

Closed Source ★ 52.0
🤖
MiniMax-M3-MXFP8
MiniMaxAI

MiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters.

Open Source ★ 45.0 ↓ 363.6K
🤖
MiniMax-M3
MiniMaxAI

MiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters.

Open Source ★ 45.0 ↓ 194.5K
🤖
Kimi-K2.7-Code
moonshotai

Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long-horizon coding tasks, it strengthens end-to-end task completion across complex software engineering workflows while improving token efficiency, reducing thinkin…

Code ★ 43.0 ↓ 229.3K
🤖
MiMo-V2.5-Pro
XiaomiMiMo

🤗 HuggingFace   📰 Blog   🎨 Xiaomi MiMo API Platform   🗨️ Xiaomi MiMo Studio  

Open Source ★ 43.0 ↓ 48.2K
🤖
MiMo-V2.5-Pro-FP4-DFlash
XiaomiMiMo

🎨 Xiaomi MiMo API Platform (Request Access)     🗨️ Xiaomi MiMo Studio (Free Trial)

Open Source ★ 43.0 ↓ 491
🤖
Hy3-preview
tencent

           

Open Source ★ 42.0 ↓ 61.3K