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. unsloth/Llama-3.2-1B-Instruct
  4. Speed on AMD Instinct MI250X
AMD Instinct MI250X~628 tok/s (Q4)

unsloth/Llama-3.2-1B-Instruct speed on AMD Instinct MI250X

Quantization-specific throughput and VRAM requirements for unsloth/Llama-3.2-1B-Instruct running on AMD Instinct MI250X.

Speed Snapshot
Topline estimate from compatibility data
Modelunsloth/Llama-3.2-1B-Instruct
GPUAMD Instinct MI250X
Q4 speed628 tok/s
Q4 VRAM required1GB
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
Q41GB128GB628 tok/s✅ Fits
Q81GB128GB392 tok/s✅ Fits
FP162GB128GB213 tok/s✅ Fits
Back to unsloth/Llama-3.2-1B-InstructQ4 requirement pageFull compatibility breakdown