RTX 4090~68 tok/s (Q4)

zai-org/GLM-4.7-Flash speed on RTX 4090

Quantization-specific throughput and VRAM requirements for zai-org/GLM-4.7-Flash running on RTX 4090.

Speed Snapshot

Topline estimate from compatibility data

Modelzai-org/GLM-4.7-Flash

GPURTX 4090

Q4 speed68 tok/s

Q4 VRAM required18GB

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	18GB	24GB	68 tok/s	✅ Fits
Q8	35GB	24GB	42 tok/s	❌ Not recommended
FP16	70GB	24GB	23 tok/s	❌ Not recommended