RX 9070~92 tok/s (Q4)

Qwen/Qwen3-Embedding-8B speed on RX 9070

Quantization-specific throughput and VRAM requirements for Qwen/Qwen3-Embedding-8B running on RX 9070.

Speed Snapshot

Topline estimate from compatibility data

ModelQwen/Qwen3-Embedding-8B

GPURX 9070

Q4 speed92 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	16GB	92 tok/s	✅ Fits
Q8	9GB	16GB	58 tok/s	✅ Fits
FP16	17GB	16GB	30 tok/s	❌ Not recommended