AMD Instinct MI300X~87 tok/s (Q4)

XiaomiMiMo/MiMo-V2-Flash speed on AMD Instinct MI300X

Quantization-specific throughput and VRAM requirements for XiaomiMiMo/MiMo-V2-Flash running on AMD Instinct MI300X.

Speed Snapshot

Topline estimate from compatibility data

ModelXiaomiMiMo/MiMo-V2-Flash

GPUAMD Instinct MI300X

Q4 speed87 tok/s

Q4 VRAM required174GB

Data Source

Calculation and benchmark status

Speed values come from the compatibility dataset (`estimatedTokensPerSec`) and are sorted by quantization.

For full verdict logic and alternate GPUs, see the canonical compatibility page.

Quantization Speed Table

Quantization	VRAM needed	VRAM available	Speed	Verdict
Q4	174GB	192GB	87 tok/s	✅ Fits
Q8	347GB	192GB	68 tok/s	❌ Not recommended
FP16	693GB	192GB	37 tok/s	❌ Not recommended