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. microsoft/Phi-3-medium-128k-instruct
  4. Speed on NVIDIA H200 SXM 141GB
NVIDIA H200 SXM 141GB~515 tok/s (Q4)

microsoft/Phi-3-medium-128k-instruct speed on NVIDIA H200 SXM 141GB

Quantization-specific throughput and VRAM requirements for microsoft/Phi-3-medium-128k-instruct running on NVIDIA H200 SXM 141GB.

Speed Snapshot
Topline estimate from compatibility data
Modelmicrosoft/Phi-3-medium-128k-instruct
GPUNVIDIA H200 SXM 141GB
Q4 speed515 tok/s
Q4 VRAM required7GB
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
Q47GB141GB515 tok/s✅ Fits
Q814GB141GB385 tok/s✅ Fits
FP1629GB141GB211 tok/s✅ Fits
Back to microsoft/Phi-3-medium-128k-instructQ4 requirement pageFull compatibility breakdown