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 ↗ · 2026-11-12T04:15:28.848605624ZTransparency & Governance
- Foundation Model Transparency Index 2025 · 26 / 100 · Company disclosure assessment Source assessment ↗
450 indexed models
450 matching models
qwen/qwen3-embedding-8b
The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model
- Context window
- 40,960
- Input modalities
- text
- Output modalities
- embeddings
- Capabilities
- embeddings
Benchmarks
Inference prices
- Published price : $0.01 / input_tokens_per_million · openRouter ↗
- Published price : $0.00 / output_tokens_per_million · openRouter ↗
vertexAI/publishers/hf-qwen/models/qwen3guard-gen-0.6b@001
- Input modalities
- text
- Output modalities
- text
vertexAI/publishers/hf-qwen/models/qwen3guard-gen-4b@001
- Input modalities
- text
- Output modalities
- text
vertexAI/publishers/hf-qwen/models/qwen3guard-gen-8b@001
- Input modalities
- text
- Output modalities
- text
qwen/qwen3-next-80b-a3b-instruct-2509
Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual use, while remaining robust on alignm
- Context window
- 262,144
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 9.6
- OpenCompass LLM: 81.3%
- OpenRouter Benchmarks: 71.324%
Inference prices
- Published price : $0.09 / input_tokens_per_million · openRouter ↗
- Published price : $1.10 / output_tokens_per_million · openRouter ↗
azureFoundry/HuggingFace/qwen-qwen3-next-80b-a3b-instruct-fp8@3
`Qwen/Qwen3-Next-80B-A3B-Instruct-FP8` powered by vLLM - [Original Model Card](https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct-FP8) - [vLLM Documentation](https://docs.vllm.ai) ## Chat Completions API ### Send Request You can use cURL or any REST Client to send a requ
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/qwen-qwen3-next-80b-a3b-instruct-gguf@2
`Qwen/Qwen3-Next-80B-A3B-Instruct-GGUF` with Q8_0 quantization, powered by llama.cpp - [Original Model Card](https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct-GGUF) - [llama.cpp Documentation](https://github.com/ggml-org/llama.cpp) ## GGUF **GGUF** is a binary file forma
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/qwen-qwen3-next-80b-a3b-thinking-fp8@1
`Qwen/Qwen3-Next-80B-A3B-Thinking-FP8` powered by vLLM - [Original Model Card](https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking-FP8) - [vLLM Documentation](https://docs.vllm.ai) ## Chat Completions API ### Send Request You can use cURL or any REST Client to send a requ
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/qwen-qwen3-next-80b-a3b-thinking-gguf@2
`Qwen/Qwen3-Next-80B-A3B-Thinking-GGUF` with Q8_0 quantization, powered by llama.cpp - [Original Model Card](https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking-GGUF) - [llama.cpp Documentation](https://github.com/ggml-org/llama.cpp) ## GGUF **GGUF** is a binary file forma
- Input modalities
- text
- Output modalities
- text
siliconFlow/Qwen/Qwen3-Omni-30B-A3B-Captioner
Qwen3-Omni-30B-A3B-Captioner is a Vision-Language Model (VLM) from Alibaba's Qwen team, part of the Qwen3 series. It is specifically designed for generating high-quality, detailed, and accurate image captions. Based on a 30B total parameter Mixture of Experts (MoE) architecture,
- Maximum output
- 65,536
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, structuredOutputs, toolCalling, visionInput
siliconFlow/Qwen/Qwen3-Omni-30B-A3B-Instruct
Qwen3-Omni-30B-A3B-Instruct is a member of the latest Qwen3 series from Alibaba's Qwen team. It is a Mixture of Experts (MoE) model with 30 billion total parameters and 3 billion active parameters, which effectively reduces inference costs while maintaining powerful performance.
- Maximum output
- 65,536
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, structuredOutputs, toolCalling, visionInput
Benchmarks
siliconFlow/Qwen/Qwen3-Omni-30B-A3B-Thinking
Qwen3-Omni-30B-A3B-Thinking is the core "Thinker" component within the Qwen3-Omni omni-modal model's "Thinker-Talker" architecture. It is specifically designed to process multimodal inputs, including text, audio, images, and video, and to execute complex chain-of-thought reasonin
- Maximum output
- 65,536
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, structuredOutputs, toolCalling, visionInput
huggingface/Qwen/Qwen3-Reranker-4B
- Capabilities
- rerank
huggingface/Qwen/Qwen3-TTS-12Hz-0.6B-Base
huggingface/Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice
huggingface/Qwen/Qwen3-TTS-12Hz-1.7B-Base
huggingface/Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
qwen/qwen3-vl-235b-a22b-instruct
Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table extraction, multilingual OCR). The seri
- Context window
- 262,144
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, structuredOutputs, toolCalling, visionInput
Benchmarks
- Artificial Analysis: 9.9
- OpenRouter Benchmarks: 48%
Inference prices
- Published price : $0.20 / input_tokens_per_million · deepInfra ↗
- Published price : $0.88 / output_tokens_per_million · deepInfra ↗