NVIDIA H200 SXM 141GB~138 tok/s (Q4)

RedHatAI/Llama-3.2-90B-Vision-Instruct-FP8-dynamic speed on NVIDIA H200 SXM 141GB

Quantization-specific throughput and VRAM requirements for RedHatAI/Llama-3.2-90B-Vision-Instruct-FP8-dynamic running on NVIDIA H200 SXM 141GB.

Speed Snapshot

Topline estimate from compatibility data

ModelRedHatAI/Llama-3.2-90B-Vision-Instruct-FP8-dynamic

GPUNVIDIA H200 SXM 141GB

Q4 speed138 tok/s

Q4 VRAM required44GB

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	44GB	141GB	138 tok/s	✅ Fits
Q8	88GB	141GB	90 tok/s	✅ Fits
FP16	176GB	141GB	57 tok/s	❌ Not recommended