AMD Instinct MI250X~261 tok/s (Q4)

mlx-community/gpt-oss-20b-MXFP4-Q8 speed on AMD Instinct MI250X

Quantization-specific throughput and VRAM requirements for mlx-community/gpt-oss-20b-MXFP4-Q8 running on AMD Instinct MI250X.

Speed Snapshot

Topline estimate from compatibility data

Modelmlx-community/gpt-oss-20b-MXFP4-Q8

GPUAMD Instinct MI250X

Q4 speed261 tok/s

Q4 VRAM required10GB

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	10GB	128GB	261 tok/s	✅ Fits
Q8	20GB	128GB	187 tok/s	✅ Fits
FP16	41GB	128GB	98 tok/s	✅ Fits