AMD Instinct MI300X~165 tok/s (Q4)

AI-MO/Kimina-Prover-72B speed on AMD Instinct MI300X

Quantization-specific throughput and VRAM requirements for AI-MO/Kimina-Prover-72B running on AMD Instinct MI300X.

Speed Snapshot

Topline estimate from compatibility data

ModelAI-MO/Kimina-Prover-72B

GPUAMD Instinct MI300X

Q4 speed165 tok/s

Q4 VRAM required35GB

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	35GB	192GB	165 tok/s	✅ Fits
Q8	70GB	192GB	116 tok/s	✅ Fits
FP16	141GB	192GB	56 tok/s	✅ Fits