AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models
Canzona: A Unified, Asynchronous, and Load-Balanced Framework for Distributed Matrix-based Optimizers
Organization Card
Welcome to Qwen 👋
This is the organization of Qwen, which refers to the large language model family built by Alibaba Cloud. In this organization, we continuously release large language models (LLM), large multimodal models (LMM), and other AGI-related projects. Feel free to visit Qwen Chat and enjoy our latest models!
-
Qwen/Qwen3-ASR-1.7B
Automatic Speech Recognition • 2B • Updated • 210k • 438 -
Qwen/Qwen3-ASR-0.6B
Automatic Speech Recognition • 0.9B • Updated • 44.2k • 191 -
Qwen/Qwen3-ForcedAligner-0.6B
Automatic Speech Recognition • 0.9B • Updated • 19.6k • 80 -
Qwen3-ASR Demo
🎙95Transcribe audio to text with timestamps and playback
-
Qwen/Qwen3-ASR-1.7B
Automatic Speech Recognition • 2B • Updated • 210k • 438 -
Qwen/Qwen3-ASR-0.6B
Automatic Speech Recognition • 0.9B • Updated • 44.2k • 191 -
Qwen/Qwen3-ForcedAligner-0.6B
Automatic Speech Recognition • 0.9B • Updated • 19.6k • 80 -
Qwen3-ASR Demo
🎙95Transcribe audio to text with timestamps and playback
spaces
30
Running
on
Zero
Featured
95
Qwen3-ASR Demo
🎙
Transcribe audio to text with timestamps and playback
Running
on
Zero
Featured
1.34k
Qwen3-TTS Demo
🎙
Generate speech with custom, cloned, or preset voices
Running
on
Zero
Featured
297
Qwen Image 2512
👀
Generate high‑quality images from detailed text prompts
Running
on
Zero
303
Qwen Image Edit 2511
🏆
Edit images based on natural language instructions
Running
on
Zero
Featured
430
Qwen Image Layered
🚀
Decompose an image into separate layers and download them
Running
99
Qwen3 TTS Voice Design
📈
Generate custom voice audio from text and description
models
412
Qwen/Qwen3-Coder-Next-GGUF
Text Generation
•
80B
•
Updated
•
25.6k
•
127
Qwen/Qwen3-Coder-Next
Text Generation
•
80B
•
Updated
•
113k
•
•
676
Qwen/Qwen3-Coder-Next-Base
Text Generation
•
80B
•
Updated
•
1.19k
•
47
Qwen/Qwen3-Coder-Next-FP8
Text Generation
•
80B
•
Updated
•
72.9k
•
•
59
Qwen/Qwen3-ForcedAligner-0.6B
Automatic Speech Recognition
•
0.9B
•
Updated
•
19.6k
•
80
Qwen/Qwen3-ASR-0.6B
Automatic Speech Recognition
•
0.9B
•
Updated
•
44.2k
•
191
Qwen/Qwen3-ASR-1.7B
Automatic Speech Recognition
•
2B
•
Updated
•
210k
•
438
Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign
Text-to-Speech
•
2B
•
Updated
•
204k
•
240
Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice
Text-to-Speech
•
0.9B
•
Updated
•
119k
•
102
Qwen/Qwen3-TTS-Tokenizer-12Hz
Audio-to-Audio
•
Updated
•
60.1k
•
41
datasets
7
Qwen/RationaleRM
Preview
•
Updated
•
754
•
11
Qwen/DeepPlanning
Viewer
•
Updated
•
2.14k
•
758
•
170
Qwen/Qwen3GuardTest
Viewer
•
Updated
•
2.44k
•
884
•
25
Qwen/PolyMath
Viewer
•
Updated
•
9k
•
7.36k
•
41
Qwen/CodeElo
Viewer
•
Updated
•
408
•
170
•
28
Qwen/ProcessBench
Viewer
•
Updated
•
3.4k
•
3.31k
•
57
Qwen/P-MMEval
Viewer
•
Updated
•
19.7k
•
131
•
14