RTX 5090~387 tok/s (Q4)

meta-llama/Llama-3.2-3B-Instruct speed on RTX 5090

Quantization-specific throughput and VRAM requirements for meta-llama/Llama-3.2-3B-Instruct running on RTX 5090.

Speed Snapshot

Topline estimate from compatibility data

Modelmeta-llama/Llama-3.2-3B-Instruct

GPURTX 5090

Q4 speed387 tok/s

Q4 VRAM required2GB

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	2GB	32GB	387 tok/s	✅ Fits
Q8	3GB	32GB	262 tok/s	✅ Fits
FP16	6GB	32GB	134 tok/s	✅ Fits