Speedy runs Qwen3.8-Flash-Next with up to 1M-token context on one or two RTX cards
Original titleDevDock-AI/Speedy
- Outlet
- GitHub
- Published
- Importance
- 2/5
- Trending
- 14
Summary
Speedy is an optimized fork of Strata that runs Qwen3.8-Flash-Next, a 125B mixture-of-experts model, up to 1-million-token context on one or two RTX cards, tuned on an RTX 3080 with 10 GB of memory.
Original excerpt
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. · topics: cuda, inference, llama, llama-cpp, llm, long-context, mixture-of-experts, multi-gpu, nvidia, qwen, rtx, rtx-3080, strata
#llm#inference#moe#qwen