Skip to content
drmihirbrahme / midgeView on GitHub
Tiny engine, immense models — run large MoE LLMs (gpt-oss, Mixtral, Qwen3-MoE) on ordinary machines by streaming experts from disk. OpenAI-compatible server with tool calling + hybrid cloud relay; CPU, Apple Silicon (MLX) & CUDA.
☆13Aug 21, 2026Updated 3 months ago

Alternatives and similar repositories for midge

Users that are interested in midge are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?