R_REDDYX.XYZ
AIC++★ 144⑂ 9 forksMIT

Betelgeuse-AI/Betelgeuse

MoE Inference on Consumer GPUs

Runs frontier-scale MoE models on RTX 3060 (12GB VRAM) by keeping dense layers on GPU and swapping experts from NVMe into a bounded VRAM pool.

// KEY FEATURES

  • Offloads routed experts to NVMe, loads only active experts into 12GB VRAM pool
  • Keeps dense computation resident on GPU for low-latency token generation
  • Supports frontier-scale MoE models on 16GB RAM + consumer GPU hardware
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

LoRa Base Station★ 144MEMEX: MEMORY FOR AI AGENTS★ 144EVOQUANT: AI AGENT FOR QUANTITATIVE RESEARCH★ 144Uncensored Video Generator★ 145AI-GoldenAPP Catalog★ 143Noumena Code TUI★ 146

← FULL CATALOG

Betelgeuse-AI/Betelgeuse — MoE Inference on Consumer GPUs