AI Agent Hub

LLM Models · Qwen

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

104 models from Qwen Compare
Qwen3.5-2B logo
Qwen3.5-2B
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. In light of its parameter scale, the intende…

open-source 2.0B ★ 7.0 ↓ 2.8M
Qwen3.5-2B-Base logo
Qwen3.5-2B-Base
Qwen

[!Note] This repository contains model weights and configuration files for the pre-trained only model in the Hugging Face Transformers format. These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, etc. The intended use cases are fine-tuning, in-context lear…

open-source 2.0B ★ 7.0 ↓ 1.4M
Qwen3.5-0.8B logo
Qwen3.5-0.8B
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. In light of its parameter scale, the intende…

open-source 0.8B ★ 5.0 ↓ 2.5M
Qwen3-0.6B logo
Qwen3-0.6B
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 0.6B ↓ 22.7M
Qwen3-8B logo
Qwen3-8B
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 8.0B ↓ 13.6M
Qwen2.5-7B-Instruct logo
Qwen2.5-7B-Instruct
Qwen

Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:

open-source 7.0B ↓ 10.6M
Qwen3-VL-8B-Instruct logo
Qwen3-VL-8B-Instruct
Qwen

Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.

multimodal 8.0B ↓ 9.6M
Qwen2.5-VL-7B-Instruct logo
Qwen2.5-VL-7B-Instruct
Qwen

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

multimodal 7.0B ↓ 8M
Qwen2.5-1.5B-Instruct logo
Qwen2.5-1.5B-Instruct
Qwen

Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:

open-source 1.54B ↓ 7.7M
Qwen2.5-3B-Instruct logo
Qwen2.5-3B-Instruct
Qwen

Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:

open-source 3.0B ↓ 7.6M
Qwen3-4B logo
Qwen3-4B
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,…

reasoning 4.0B ↓ 6.4M
Qwen2.5-0.5B-Instruct logo
Qwen2.5-0.5B-Instruct
Qwen

Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:

open-source 0.5B ↓ 6M