NVIDIA H100 PCIe 80GB~106 tok/s (Q4)

RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w4a16 speed on NVIDIA H100 PCIe 80GB

Quantization-specific throughput and VRAM requirements for RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w4a16 running on NVIDIA H100 PCIe 80GB.

Speed Snapshot

Topline estimate from compatibility data

ModelRedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w4a16

GPUNVIDIA H100 PCIe 80GB

Q4 speed106 tok/s

Q4 VRAM required34GB

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	34GB	80GB	106 tok/s	✅ Fits
Q8	68GB	80GB	70 tok/s	✅ Fits
FP16	137GB	80GB	38 tok/s	❌ Not recommended