RX 7900 XT~43 tok/s (Q4)

Qwen/Qwen2.5-Coder-32B-Instruct speed on RX 7900 XT

Quantization-specific throughput and VRAM requirements for Qwen/Qwen2.5-Coder-32B-Instruct running on RX 7900 XT.

Speed Snapshot

Topline estimate from compatibility data

ModelQwen/Qwen2.5-Coder-32B-Instruct

GPURX 7900 XT

Q4 speed43 tok/s

Q4 VRAM required17GB

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	17GB	20GB	43 tok/s	✅ Fits
Q8	34GB	20GB	30 tok/s	❌ Not recommended
FP16	67GB	20GB	17 tok/s	❌ Not recommended