expert-offloading

Open repos and models their makers tagged expert-offloading, most starred first. The same for everyone.

AI on my own machineRepo

moe

Qwen3.6-35B-A3B at ~68 tok/s on a 6 GB laptop GPU: expert-level VRAM caching + CPU offload + multi-token prediction in CUDA. ~1.9x tuned llama.cpp / ik_llama.cpp (MTP vs no speculative decoding).

  • 10
  • Cuda
  • MIT
  • 3 wk ago
Search GitHub and Hugging Face for expert-offloading

Get , open it once and sign in. Then come back here and press the button again.

expert-offloading: open source repos and models on Take My Repo