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-4-multimodal-instruct
  4. Speed on Intel Arc Pro A40
Intel Arc Pro A40~48 tok/s (Q4)

microsoft/Phi-4-multimodal-instruct speed on Intel Arc Pro A40

Quantization-specific throughput and VRAM requirements for microsoft/Phi-4-multimodal-instruct running on Intel Arc Pro A40.

Speed Snapshot
Topline estimate from compatibility data
Modelmicrosoft/Phi-4-multimodal-instruct
GPUIntel Arc Pro A40
Q4 speed48 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.

Open full compatibility report

Quantization Speed Table

QuantizationVRAM neededVRAM availableSpeedVerdict
Q44GB6GB48 tok/s✅ Fits
Q87GB6GB32 tok/s❌ Not recommended
FP1615GB6GB15 tok/s❌ Not recommended
Back to microsoft/Phi-4-multimodal-instructQ4 requirement pageFull compatibility breakdown