Instinct MI100 x4

Amd · 32 GB VRAM

1recorded run

132.4best tok/s

1sourced

How it compares — 32 GB per card · multi-GPU

Best verified tok/s per GPU in this VRAM tier — compare any two like-for-like.

Evidence: 1 sourced run · 1 independent source · first recorded Aug 24, 2026. What these labels mean.

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
Instinct MI100 x4 · 32 GB	Qwen3.8-27B	INT8	vllm https://github.com/curvedinf/vllm-gf…	64000	132.4 ✓	1202.7	128.0	src