RX 7900 XTX~80 tok/s (Q4)

Mlx Community Gpt Oss 20B Mxfp4 Q8 speed on RX 7900 XTX

Quantization-specific throughput and VRAM requirements for Mlx Community Gpt Oss 20B Mxfp4 Q8 running on RX 7900 XTX.

Speed Snapshot

Topline estimate from compatibility data

ModelMlx Community Gpt Oss 20B Mxfp4 Q8

GPURX 7900 XTX

Q4 speed80 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	24GB	80 tok/s	✅ Fits
Q8	20GB	24GB	56 tok/s	✅ Fits
FP16	40GB	24GB	30 tok/s	❌ Not recommended