DeepSeek-V3.2
Collection
4 items • Updated • 542
🎑 September 2025 - China Open Source Highlights
-
-
deepseek-ai/DeepSeek-V3.1-Terminus
Text Generation • Updated • 3.64k • • 363 -
zai-org/GLM-4.6
Text Generation • 357B • Updated • 36.1k • • 1.21k -
Kwai-Klear/Klear-46B-A2.5B-Base
Text Generation • 46B • Updated • 34 • 30 -
GAIR/LIMI
Text Generation • Updated • 28 • 31 -
moonshotai/Kimi-K2-Instruct-0905
Text Generation • 1T • Updated • 457k • • 701 -
openbmb/MiniCPM4.1-8B
Text Generation • 8B • Updated • 29.6k • 390 -
openbmb/VoxCPM-0.5B
Text-to-Speech • Updated • 1.56k • 797 -
inclusionAI/Ring-mini-2.0
Text Generation • 16B • Updated • 207 • 182 -
bytedance-research/HuMo
Image-to-Video • Updated • 79 • 216 -
unitreerobotics/UnifoLM-WMA-0-Base
Robotics • Updated • 60 -
OpenGVLab/ScaleCUA-3B
Image-Text-to-Text • 4B • Updated • 86 • 11 -
OpenGVLab/InternVL3_5-241B-A28B-Flash
Image-Text-to-Text • 242B • Updated • 10 • 7 -
FireRedTeam/FireRedTTS2
Updated • 66 -
BAAI/RoboBrain-X0-Preview
Robotics • 4B • Updated • 2 • 11 -
baidu/ERNIE-4.5-21B-A3B-Thinking
Text Generation • 22B • Updated • 10.8k • 782 -
baidu/Qianfan-VL-70B
Image-Text-to-Text • 72B • Updated • 53 • 38 -
baidu/Qianfan-VL-3B
Image-Text-to-Text • 4B • Updated • 414 • 28 -
tencent/Hunyuan-MT-7B
Translation • 8B • Updated • 26.8k • 553 -
TencentARC/IC-Custom
Image-to-Image • Updated • 19 • 16 -
tencent/HunyuanWorld-Voyager
Image-to-Video • Updated • 132 • 606 -
tencent/HunyuanImage-2.1
Text-to-Image • Updated • 215 • • 380 -
tencent/Hunyuan3D-Part
Updated • 1.45k • 534 -
tencent/HunyuanImage-3.0
Text-to-Image • Updated • 17.6k • • 1.07k -
tencent/POINTS-Reader
Image-Text-to-Text • 4B • Updated • 144 • 102 -
tencent/Hunyuan3D-Omni
Image-to-3D • Updated • 1.46k • 165 -
tencent/SRPO
Text-to-Image • Updated • 210 • • 976 -
inclusionAI/Ring-1T-preview
Text Generation • Updated • 34 • 268 -
inclusionAI/Ling-mini-2.0
Text Generation • 16B • Updated • 18.2k • 193 -
inclusionAI/Ring-mini-linear-2.0
Text Generation • 16B • Updated • 240 • 89 -
inclusionAI/Ling-flash-base-2.0
Text Generation • 106B • Updated • 388 • 32 -
inclusionAI/Ring-flash-2.0
Text Generation • 103B • Updated • 116 • 102 -
XiaomiMiMo/MiMo-Audio-7B-Base
Any-to-Any • 8B • Updated • 63 • 49 -
XiaomiMiMo/MiMo-Audio-7B-Instruct
Any-to-Any • 8B • Updated • 42k • 153 -
Wan-AI/Wan2.2-Animate-14B
Video-to-Video • Updated • 22.3k • 1.14k -
Qwen/Qwen3-Next-80B-A3B-Instruct
Text Generation • 81B • Updated • 281k • • 1.01k -
Alibaba-NLP/Tongyi-DeepResearch-30B-A3B
Text Generation • 31B • Updated • 18.3k • 810 -
Qwen/Qwen3Guard-Stream-8B
Feature Extraction • 8B • Updated • 3.61k • 35 -
Qwen/Qwen3Guard-Gen-0.6B
Text Generation • 0.8B • Updated • 306k • 68 -
Qwen/Qwen3-VL-235B-A22B-Thinking
Image-Text-to-Text • 236B • Updated • 247k • • 389 -
Qwen/Qwen3-VL-235B-A22B-Instruct
Image-Text-to-Text • 236B • Updated • 1.04M • • 383 -
BAAI/RoboBrain-X0-Dataset
Viewer • Updated • 61.6k • 189 • 10 -
BAAI/ROME
Viewer • Updated • 281 • 128 • 5 -
Lk123/InfoSeek
Preview • Updated • 1.33k • 50 -
OpenMOSS-Team/VehicleWorld
Viewer • Updated • 1.29k • 80 • 7 -
FireRedTTS2
🔥34Long-form multi-speaker dialogue generation
-
VoxCPM 0.5B
🐢44Generate expressive speech from text with optional voice cloning
-
Wan2.2 Animate
👁5.11kWan2.2 Animate
-
Qwen3 Omni Demo
⚡262Chat with multimodal AI using text, audio, images, and video
-
Qwen3 TTS Demo
🚀400Generate spoken audio from text in many voices and languages
-
Qwen3 VL Demo
😻421Chat with an AI that understands text, images, and videos
-
Qwen3 ASR Demo
👀260Transcribe audio files to text with language detection
-
Qwen3 Livetranslate Demo
🏃134Translate speech live with text and audio output
-
IC Custom
🎨38IC-Custom is designed for diverse image customization.
-
Hunyuan3D Part
☯72Segment and generate parts from 3D models