AIRust★ 68⑂ 4 forksApache-2.0
1picassoai/coachwhip
Mixture-of-Experts LLM Engine
Runs an 80‑billion‑parameter mixture‑of‑experts language model on Apple Silicon, fitting within 16 GB RAM.
// KEY FEATURES
- Executes MoE inference with expert routing optimized for Apple’s Neural Engine.
- Loads 80B parameter model using quantized weights, staying under 16 GB memory.
- Provides low‑latency text generation via Rust‑based async pipeline on macOS.
New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram