L
localai.computer
ModelsGPUsSystemsAI SetupsBuildsOpenClawMethodology

Resources

  • Methodology
  • Submit Benchmark
  • About

Browse

  • AI Models
  • GPUs
  • PC Builds

Guides

  • OpenClaw Guide
  • How-To Guides

Legal

  • Privacy
  • Terms
  • Contact

© 2025 localai.computer. Hardware recommendations for running AI models locally.

ℹ️We earn from qualifying purchases through affiliate links at no extra cost to you. This supports our free content and research.

  1. Home
  2. Models
  3. Qwen/Qwen2.5-72B-Instruct
  4. Speed on NVIDIA H100 SXM5 80GB
NVIDIA H100 SXM5 80GB~99 tok/s (Q4)

Qwen/Qwen2.5-72B-Instruct speed on NVIDIA H100 SXM5 80GB

Quantization-specific throughput and VRAM requirements for Qwen/Qwen2.5-72B-Instruct running on NVIDIA H100 SXM5 80GB.

Speed Snapshot
Topline estimate from compatibility data
ModelQwen/Qwen2.5-72B-Instruct
GPUNVIDIA H100 SXM5 80GB
Q4 speed99 tok/s
Q4 VRAM required35GB
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.

Open full compatibility report

Quantization Speed Table

QuantizationVRAM neededVRAM availableSpeedVerdict
Q435GB80GB99 tok/s✅ Fits
Q870GB80GB73 tok/s✅ Fits
FP16141GB80GB37 tok/s❌ Not recommended
Back to Qwen/Qwen2.5-72B-InstructQ4 requirement pageFull compatibility breakdown