R_REDDYX.XYZ
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
← Full catalog·Full index

// SIMILAR REPOSITORIES

Analytic Context Layer★ 71Passive Meshtastic LoRa Reception★ 70PH-Content Content Management★ 72Local AI Generator★ 72Science in Real Time★ 72Training AI to Launch Meta Ads★ 70

← FULL CATALOG

DevDock-AI/Speedy — 125B MoE Inference on RTX | REDDYX AI