Kimi K3 runs on AMD MI355X at 952 tok/s per node, claim says
AccBalanced · x · 2026-08-04
A quoted post says the team got Kimi K3 running on AMD MI355X at 952 tok/s/node and 118 tok/s single-stream.
The claim also says the setup delivers 3.8× the aggregate throughput per node and 1.3× the single-stream decode of B200, while beating B300 on performance per dollar at 48 vs. 33 tok/s/$. More details were promised in replies.
Related event: AMD MI355X Runs Kimi K3 at 952 tok/s, Outperforming B200(6 posts)→
More from Infra
- NVIDIA launches RTX Spark for local AI on Windows PCs — ostrisai · 2026-10-16
- SkyRL ships Day-0 RL support for Beam with +62% LoRA decode throughput in vLLM — vllm_project · 2026-10-16
- DFlash2 delivers up to 3.03x decode-only speedup for Beam across five benchmarks — vllm_project · 2026-10-16
- vLLM's Beam serving kernels cut GB200 forward time from 8.15 to 6.47 ms at TP8 batch 128 — vllm_project · 2026-10-16
- Reflection's 501B MoE Beam hits 463 tok/s on 8x GB200 with NVFP4 at day 0 — zhyncs42 · 2026-10-16
- Gemma 4 31B QAT on one 24GB card: 46 tok/s plain, ~80 with draft model on RTX 4090 — Subject_Poet_3861 · 2026-10-16