NVIDIA H100 PCIe 80GB~321 tok/s (Q4)

microsoft/Phi-3.5-mini-instruct speed on NVIDIA H100 PCIe 80GB

Quantization-specific throughput and VRAM requirements for microsoft/Phi-3.5-mini-instruct running on NVIDIA H100 PCIe 80GB.

Speed Snapshot

Topline estimate from compatibility data

Modelmicrosoft/Phi-3.5-mini-instruct

GPUNVIDIA H100 PCIe 80GB

Q4 speed321 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	80GB	321 tok/s	✅ Fits
Q8	7GB	80GB	206 tok/s	✅ Fits
FP16	15GB	80GB	127 tok/s	✅ Fits