Repo

VibeBlade

@kevin046by Kevin Lin · VibeDrift Inc.

0

VibeDrift - Run any LLM on your own hardware. Bypass the VRAM wall with CPU/RAM inference, MOE expert offloading, and 4-bit quantization. No Cloud, no Subscription.

Built withPythonconstrained-decodingcpu-inferenceggufinferencellm

See what other members are building and what each project is looking for.