MusaCoder-27B

MooreThreads/MusaCoder-27B

Reinforcement Learning3.1M parametersLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
590
Total downloads
1,631
Gained 7D
Gained 30D
Likes
60
Rank · tracked models
#27,080
this week
Parameters
3.1M
Last source update
Jun 10, 2026

Downloads over time

Cumulative total downloads observed by OpenModelStats

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-08-24. Charts appear as daily observations accumulate.

Likes over time

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-08-24. Charts appear as daily observations accumulate.

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-08-24. Charts appear as daily observations accumulate.

Overview

MusaCoder-27B is a reinforcement learning model published by MooreThreads. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it 14 min ago.

Published
Jun 5, 2026
Last updated
Jun 10, 2026
Library
License
apache-2.0
Task
Reinforcement Learning
Parameters
3,054,832
Spaces
Derivative models
Velocity 7D/day
safetensorsqwen3_5CUDAMUSAGPU-KernelReinforcement-Learningreinforcement-learningenzharxiv:2606.04847base_model:Qwen/Qwen3.6-27Bbase_model:finetune:Qwen/Qwen3.6-27B

Publisher

MooreThreadsView publisher statistics →

Derived from Qwen/Qwen3.6-27B (reported by the source; parent not yet tracked).

Similar models

Models similar to MusaCoder-27B
ModelDL 30D
jatjat-project1,867
beaver-7b-v1.0-costPKU-Alignment6,092
beaver-7b-v1.0-rewardPKU-Alignment5,066
DiBO-TFBind10zpointsun685
MetaAgent-XMercury73532,858
VisualQuality-R1-7BTianheWu6,258