AIPython★ 137⑂ 17 forks
divagr18/QwenPU
Tiny LLM runs inside Qwen
Karpathy's stories260K model writes stories on a vector unit compiled into Qwen3.5-4B's weights, demonstrating LLM-in-LLM NPU execution.
// KEY FEATURES
- Compiles stories260K into Qwen3.5-4B weights for NPU inference
- Runs 260K parameter model on vector unit inside 4B model
- Generates stories via nested LLM execution on hardware accelerator
New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram