GitHub · C++
DevDock-AI/Speedy
Qwen3.8-Flash-Next (125B MoE) up to 1M context on one or two RTX cards (tuned on 3080 10gb). A measured, tuned and benchmarked fork of Strata.
- Stars
- 125
- Forks
- 8
- Stars gained in 24 hours
- +26
- Forks gained in 24 hours
- +3
Topics: cuda, inference, llama, llama-cpp, llm, long-context, mixture-of-experts, multi-gpu, nvidia, qwen
Latest data point: Nov 20, 2026 · 125 stars · 8 forks