Dev runs Qwen3.8-Flash-Next on Quad 3090s with custom P2P driver, hitting 361.7 tok/s
QuixiAI · x · 2026-09-07
Developer QuixiAI reports running nvidia/Qwen3.8-Flash-Next-NVFP4 on Quad 3090s via SlimServe, a custom serving stack, achieving 120 tok/s at concurrency 1 and 361.7 tok/s at concurrency 8. The key enabler is their own open-source P2P kernel driver (QuixiAI/open-gpu-kernel-modules) for cross-GPU peer-to-peer communication, and they say optimization is ongoing.
More from Infra
- PhD students in some countries get B200s on demand, unlike their US peers — HildeKuehne · 2026-10-23
- Nvidia's Berlin GTC spotlights humanoid robots and Vera Rubin AI supercomputing — emmanuelvivier · 2026-10-23
- Lenovo adds 5 AI Library use cases, claims 1-week deployment and up to 70% lower token cost — shashib · 2026-10-23
- Your kernel doesn't need to beat cuBLAS on every shape, argues GPU dev — blelbach · 2026-10-23
- 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