MMLForge Search models, datasets, tasks… Start free
Home › Models › Reinforcement Learning › MooreThreads/MusaCoder-27B
M

MooreThreads/MusaCoder-27B

Reinforcement Learning·MooreThreads· 893· 48
apache-2.0 Reinforcement Learning 3.1M params arxiv:2606.04847base_model:Qwen/Qwen3.6-27Bbase_model:finetune:Qwen/Qwen3.6-27B

MusaCoder: Native GPU Kernel Generation with Full-Stack Training on Moore Threads GPU

Open in MLForge Sign up free Desktop app Source ↗
# pull & run locally
pip install mlforge-sdk && mlforge pull MooreThreads/MusaCoder-27B

Model details

Task
Reinforcement Learning
Provider
MooreThreads
Parameters
3.1M
Size
51 GB
License
apache-2.0
Downloads
893
Likes
48
Paper
arXiv:2606.04847
Updated
2026-06-10

About MooreThreads/MusaCoder-27B

MusaCoder: Native GPU Kernel Generation with Full-Stack Training on Moore Threads GPU

Related Reinforcement Learning

P HumanCompatibleAI/ppo-seals-CartPole-v0 Reinforcement Learning 48.5K 17 🤗 HF P HumanCompatibleAI/ppo-Pendulum-v1 Reinforcement Learning 41.8K 6 🤗 HF P PaulVialard/ppo-Huggy Reinforcement Learning 4.6K 🤗 HF V TianheWu/VisualQuality-R1-7B Reinforcement Learning ·8.3B params 4.0K 14 🤗 HF S Tesleum/shirdel-coder-9b-claude-fable-5 Reinforcement Learning 3.7K 3 🤗 HF S mradermacher/SpatialThinker-7B-i1-GGUF Reinforcement Learning 3.6K 1 🤗 HF

Browse all Reinforcement Learning models →