AMD Instinct MI250X~460 tok/s (Q4)

swiss-ai/Apertus-8B-Instruct-2509 speed on AMD Instinct MI250X

Quantization-specific throughput and VRAM requirements for swiss-ai/Apertus-8B-Instruct-2509 running on AMD Instinct MI250X.

Speed Snapshot

Topline estimate from compatibility data

Modelswiss-ai/Apertus-8B-Instruct-2509

GPUAMD Instinct MI250X

Q4 speed460 tok/s

Q4 VRAM required4GB

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	4GB	128GB	460 tok/s	✅ Fits
Q8	9GB	128GB	315 tok/s	✅ Fits
FP16	17GB	128GB	167 tok/s	✅ Fits