SlimServe runs Qwen 3.8 Flash Next on 8x RTX 3090s at up to 1200 tok/sec decode
QuixiAI · x · 2026-09-06
The open-source inference project SlimServe (built on ds4/vllm) benchmarks Qwen 3.8 Flash Next on 8x RTX 3090s with P2P enabled: 140 tok/sec decode at C1 and 1200 tok/sec at C32. The author calls it "an incredible amount of valuable inference on modest hardware," offering a low-cost local-serving reference.
More from Infra
- llama.cpp team launches Llama: one-click local AI on your Mac menu bar — Hugging Face · 2026-10-23
- China's daily token use hits 500T, up 4x as average price doubles to ¥13.46 — teortaxesTex · 2026-10-23
- New all-reduce kernels deliver 12% decode speedup for DeepSeek-V4.1 on PCIe-connected GPUs — AlpinDale · 2026-10-23
- Offshore oil rigs could be converted into AI data centers powered by stranded gas — clemnt · 2026-10-23
- Same native UI, two stacks: Swift build is ~80MB Mac-only, Zig build is ~10MB cross-platform — jedisct1 · 2026-10-23
- SurfSense: an open-source local NotebookLM with MCP agents and a prompt-caching lesson — FurtiveMirth · 2026-10-23