Run Kimi K3, a 2.8T-parameter Mixture-of-Experts LLM, on a single Apple Silicon Mac. Streams MXFP4 experts on demand over HTTP into a local disk cache — fused NEON kernels, Metal/MPS compute, exact reproducible decoding, and an OpenAI-compatible API server for local chat and coding agents.
Python Updated 4 months ago 1 commits 15 stars
drift-coder|Mirror: gavamedia/deltafin (⭐15)
4 months agoE2B SandboxFirecracker microVMpython
No executable code files found in this repository.
About
Run Kimi K3, a 2.8T-parameter Mixture-of-Experts LLM, on a single Apple Silicon Mac. Streams MXFP4 experts on demand over HTTP into a local disk cache — fused NEON kernels, Metal/MPS compute, exact reproducible decoding, and an OpenAI-compatible API server for local chat and coding agents.
Readme
15 stars
2 forks