Qwen / Alibaba

About Qwen / Alibaba

Qwen Team The Qwen team aims at chasing artificial general intelligence and now focuses on building generalist models, including large language models and large multimodal models. We embrace opensource and previously we have released the Qwen model series, including the language models (Qwen), expert models (Qwen-Coder and Qwen-Math), and multimodal models (Qwen-VL and Qwen-Audio). Additionally, we have built web service and APP for users to benefit from the assistance of Qwen for your daily work and life.

The Qwen team aims at chasing artificial general intelligence and now focuses on building generalist models, including large language models and large multimodal models. We embrace opensource and previously we have released the Qwen model series, including the language models (Qwen), expert models (Qwen-Coder and Qwen-Math), and multimodal models (Qwen-VL and Qwen-Audio). Additionally, we have built web service and APP for users to benefit from the assistance of Qwen for your daily work and life. We are a group of people with diverse talents and interests. Feel free to chat with us and welcome to join us!

In the following, we provide important links for you to refer to our opensource resources.

GITHUB MODELSCOPE HUGGING FACE KAGGLE

Website ↗Hugging Face ↗

Source ↗ · 2026-11-12T04:15:28.848605624Z

Transparency & Governance

  • Foundation Model Transparency Index 2025 · 26 / 100 · Company disclosure assessment Source assessment ↗

448 indexed models

448 matching models

qwen3-30b-a3b

cheaperInference/qwen3-30b-a3b

Context window
256,000
Maximum output
16,384
Input modalities
text
Output modalities
text
Capabilities
structuredOutputs, toolCalling

Inference prices

Qwen3-30B-A3B-Base

vertexAI/publishers/qwen/models/qwen3@qwen3-30b-a3b-base

Input modalities
text
Output modalities
text

qwen-3-32b

cheaperInference/qwen-3-32b

Context window
32,000
Maximum output
8,000
Input modalities
text
Output modalities
text
Capabilities
reasoning, structuredOutputs, toolCalling

Inference prices

Qwen 3 32B

vercelAIGatewayCatalog/alibaba/qwen-3-32b

Qwen3-32B is a world-class model with comparable quality to DeepSeek R1 while outperforming GPT-4.1 and Claude Sonnet 3.7. It excels in code-gen, tool-calling, and advanced reasoning, making it an exceptional model for a wide range of production use cases.

Context window
128,000
Maximum output
8,192
Input modalities
text
Output modalities
text

qwen3-32b · azureml-alibaba v1

azureFoundry/azureml-alibaba/qwen3-32b@1

> **NOTE:** > This model is only supported for fine-tuning. Base model inference is not currently available. # Direct from Azure models Direct from Azure models are a select portfolio curated for their market-differentiated capabilities: - Secure and managed by Microsoft: Purc

Input modalities
text
Output modalities
text
Capabilities
toolCalling

Qwen3 32B (dense)

awsBedrock/qwen.qwen3-32b-v1:0

Input modalities
text
Output modalities
text

Qwen3-32B-FP8

vertexAI/publishers/qwen/models/qwen3@qwen3-32b-fp8

Input modalities
text
Output modalities
text

Qwen3-4B-Base

vertexAI/publishers/qwen/models/qwen3@qwen3-4b-base

Input modalities
text
Output modalities
text

Qwen3-4B-FP8

vertexAI/publishers/qwen/models/qwen3@qwen3-4b-fp8

Input modalities
text
Output modalities
text

Qwen3-4B-Thinking-2507

vertexAI/publishers/qwen/models/qwen3@qwen3-4b-thinking-2507

Input modalities
text
Output modalities
text

Benchmarks

  • OpenCompass LLM: 88.5%

Qwen3-4B-Thinking-2507-FP8

vertexAI/publishers/qwen/models/qwen3@qwen3-4b-thinking-2507-fp8

Input modalities
text
Output modalities
text

qwen3.5-122b-a10b

cheaperInference/qwen3.5-122b-a10b

Context window
128,000
Maximum output
65,536
Input modalities
text
Output modalities
text
Capabilities
reasoning, structuredOutputs, toolCalling

Inference prices

Qwen3.5-122B-A10B-FP8

vertexAI/publishers/qwen/models/qwen3-5@qwen3.5-122b-a10b-fp8

Input modalities
text
Output modalities
text
Capabilities
multimodal, visionInput

qwen3.5-27b

cheaperInference/qwen3.5-27b

Context window
262,144
Maximum output
65,536
Input modalities
text, image, video
Output modalities
text
Capabilities
multimodal, reasoning, structuredOutputs, toolCalling, videoInput, visionInput

Inference prices

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace