M3.1 Flash hits 191.5k tok/s per GPU on Vera Rubin NVL72, leads open models on agent benchmarks
vllm_project · x · 2026-10-23
vLLM shared day-0 serving performance for MiniMax M3.1 Flash on NVIDIA Vera Rubin NVL72 (part 2/5): 724.9 tok/s per-user decode and 191.5k tok/s per-GPU throughput. Benchmarks: 29.6 on Agents' Last Exam, 72.5% on AutomationBench-AA (leading open models in its launch comparison) and 73.67% on DeepSWE, covering real-codebase understanding, bug fixes and feature development. Built for workflows that plan, use tools and carry tasks through.
Related event: vLLM Announces Day-0 Support for MiniMax M3.1 Flash with NVFP4 Gains(4 posts)→
More from Infra
- EPFL demos ~100GHz-spacing TFLT WDM modulator chip; expert doubts CPO fit — jwt0625 · 2026-10-24
- ai& cuts MiniMax H3 video generation from 229s to 19s across NVIDIA, AMD, Tenstorrent — DavidBennett__ · 2026-10-24
- Local AI benchmarks miss thermal throttling — a stand can boost NVIDIA Spark perf — draginol · 2026-10-24
- Cloudy: autonomous cloud research agent hand-writes Triton kernels that beat tuned vLLM by up to 15% — saurabhtwq · 2026-10-24
- Chamath: major US bank cut AWS and GCP spend, built six self-run data centers — SumitGup · 2026-10-24
- OpenRouter slide shows token usage exploding as blended cost per token keeps falling — aniketmaurya · 2026-10-24