AI Agent Hub

LLM Models · Qwen

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

104 models from Qwen Compare
Qwen3-14B-AWQ logo
Qwen3-14B-AWQ
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 14.8B ↓ 2.3M
Qwen3-VL-8B-Instruct-FP8 logo
Qwen3-VL-8B-Instruct-FP8
Qwen

This repository contains an FP8 quantized version of the Qwen3-VL-8B-Instruct model. The quantization method is fine-grained fp8 quantization with block size of 128, and its performance metrics are nearly identical to those of the original BF16 model. Enjoy!

multimodal 8.0B ↓ 2.3M
Qwen2.5-14B-Instruct-AWQ logo
Qwen2.5-14B-Instruct-AWQ
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 14.7B ↓ 2.1M
Qwen2.5-32B-Instruct logo
Qwen2.5-32B-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 32.0B ↓ 2M
Qwen2.5-VL-32B-Instruct-AWQ logo
Qwen2.5-VL-32B-Instruct-AWQ
Qwen

Latest Updates: In addition to the original formula, we have further enhanced Qwen2.5-VL-32B's mathematical and problem-solving abilities through reinforcement learning. This has also significantly improved the model's subjective user experience, with response styles adjusted to…

multimodal 32.0B ↓ 2M
Qwen2.5-Coder-14B-Instruct logo
Qwen2.5-Coder-14B-Instruct
Qwen

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings…

code 14.7B ↓ 2M
Qwen3-1.7B-Base logo
Qwen3-1.7B-Base
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. Building upon extensive advancements in training data, model architecture, and optimization techniques, Qwen3 delivers the followin…

open-source 1.7B ↓ 1.9M
Qwen2.5-Coder-14B-Instruct-AWQ logo
Qwen2.5-Coder-14B-Instruct-AWQ
Qwen

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings…

code 14.7B ↓ 1.9M
Qwen3-4B-Base logo
Qwen3-4B-Base
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. Building upon extensive advancements in training data, model architecture, and optimization techniques, Qwen3 delivers the followin…

open-source 4.0B ↓ 1.9M
Qwen2-VL-2B-Instruct logo
Qwen2-VL-2B-Instruct
Qwen

We're excited to unveil Qwen2-VL , the latest iteration of our Qwen-VL model, representing nearly a year of innovation.

multimodal 2.0B ↓ 1.8M
Qwen3-14B logo
Qwen3-14B
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 14.8B ↓ 1.8M
Qwen3-8B-AWQ logo
Qwen3-8B-AWQ
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 ↓ 1.8M