AMD MI355X Runs Kimi K3 at 952 tok/s/node, Outperforming B200
AnushElangovan · x · 2026-08-02
According to @gpusteve, his team achieved 952 tok/s per node aggregate throughput and 118 tok/s single-stream on AMD MI355X with Kimi K3. This is 3.8x aggregate throughput and 1.3x single-stream decode compared to NVIDIA B200, and beats B300 on performance per dollar: 48 vs 33 tok/s/$.
Related event: AMD MI355X Runs Kimi K3 at 952 tok/s, Outperforming B200(6 posts)→
More from Infra
- Valtz v0.1.0.11 adds FLUX.3 support, local image gen up to 4K on Mac — TgoAI · 2026-10-16
- Baidu open-sources FlashMask: up to 1.55x faster than FlashAttention-4 for long-context training — BaiduResearch · 2026-10-16
- GYRO quant of Qwen3.8-Flash-Next tested: near Q3 quality at much smaller size — PlasticRevenue4601 · 2026-10-16
- RL train-sample systems are frontier AI's hardest infra problem — and a trade secret — brianryhuang · 2026-10-16
- Local tuning of GLM-5.3-Flash on 2×GB10 lifts decode from 49 to 58 tok/s — EAccelerate_42 · 2026-10-16
- 3x DGX Spark cluster runs GLM-5.3-Flash locally behind a proxy, 1.75M tokens/day at 119W — Teknium · 2026-10-16