AIC++★ 71⑂ 3 forks
DevDock-AI/Speedy
125B MoE Inference on RTX
Run Qwen3.8-Flash-Next (125B MoE) with 1M context on one or two RTX 3080 10GB cards. Tuned, benchmarked fork of Strata.
// KEY FEATURES
- Runs 125B MoE model on single RTX 3080 10GB
- Supports 1M token context window
- Measured, tuned fork of Strata inference engine
#cuda#inference#llama#llama-cpp#llm#long-context#mixture-of-experts#multi-gpu#nvidia#qwen#rtx#rtx-3080
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