MOSS-Audio-4B-Thinking

OpenMOSS-Team/MOSS-Audio-4B-Thinking

Audio Text To Text5.2B parametersLicense: apache-2.0
Tracked by OpenModelStats since September 4, 2026View on Hugging Face ↗
Downloads 30D
796
Total downloads
63.5K
Gained 7D
+78(increase)
0.1%(up) vs baseline
Gained 30D
—
Likes
38
+0 in 7D
Rank · tracked models
#35,528
276(down 276 places)this week
Parameters
5.2B
Last source update
Sep 25, 2026
Momentum
27.8
  • MOSS-Audio-4B-Thinking gained 78 downloads during the last seven tracked days.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

MOSS-Audio-4B-Thinking is a audio text to text model published by OpenMOSS-Team. OpenModelStats has tracked the model since Sep 4, 2026, most recently observing it Oct 3, 2026.

Published
Apr 11, 2026
Last updated
Sep 25, 2026
Library
—
License
apache-2.0
Task
Audio Text To Text
Parameters
5,222,820,736
Spaces
0
Derivative models
—
Velocity 7D/day
11
safetensorsmoss_audioaudiospeechmusicunderstandingmultimodalreasoningchain-of-thoughtaudio-text-to-textcustom_codeen

Similar models

Models similar to MOSS-Audio-4B-Thinking
ModelDL 30D
MOSS-Audio-4B-InstructOpenMOSS-Team16.3K
GaussianMindBAAI66
ultravox-v0_3fixie-ai3,595
ultravox-v0_2fixie-ai3,373
ultravox-v0_4fixie-ai3,653
audio-flamingo-3-hfnvidia54.3K
OpenMOSS-Team/MOSS-Audio-4B-Thinking — Downloads, Growth & Stats | OpenModelStats