AI Agent Hub

LLM Models · Qwen

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

104 models from Qwen Compare
Qwen: Qwen3.8 Max logo
Qwen: Qwen3.8 Max
qwen

Qwen3.8 Max is the flagship model in Alibaba's Qwen3.8 series, the general-availability successor to the Qwen3.8 Max Preview. It is a multimodal reasoning model intended for complex reasoning, visual understanding,...

closed-source ★ 58.0
Qwen: Qwen3.8 2.4T A95B (batch) logo
Qwen: Qwen3.8 2.4T A95B (batch)
qwen

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...

closed-source ★ 58.0
Qwen: Qwen3.8 2.4T A95B logo
Qwen: Qwen3.8 2.4T A95B
qwen

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...

closed-source ★ 58.0
Qwen: Qwen3.8 Flash logo
Qwen: Qwen3.8 Flash
qwen

Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.

closed-source ★ 56.0
Qwen3.8-27B-FP8 logo
Qwen3.8-27B-FP8
Qwen

[!Note] This repository contains FP8-quantized 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. The quantization method is fine-g…

open-source 27.0B ★ 52.0 ↓ 5.3M
Qwen3.8-27B logo
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
Qwen: Qwen3.7 Plus logo
Qwen: Qwen3.7 Plus
qwen

Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...

closed-source ★ 39.0
Qwen3.6-27B-FP8 logo
Qwen3.6-27B-FP8
Qwen

[!Note] This repository contains FP8-quantized 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, KTransformers, etc. The quantization method is fin…

open-source 27.0B ★ 38.0 ↓ 8.3M
Qwen3.6-27B logo
Qwen3.6-27B
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, KTransformers, etc.

open-source 27.0B ★ 38.0 ↓ 5.7M
Qwen: Qwen3.5 397B A17B logo
Qwen: Qwen3.5 397B A17B
qwen

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...

closed-source ★ 34.0
Qwen3.5-122B-A10B-FP8 logo
Qwen3.5-122B-A10B-FP8
Qwen

[!Note] This repository contains FP8-quantized 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, KTransformers, etc. The quantization method is fin…

multimodal 122.0B ★ 33.0 ↓ 1.8M
Qwen3.5-122B-A10B logo
Qwen3.5-122B-A10B
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, KTransformers, etc.

open-source 122.0B ★ 33.0 ↓ 863.7K