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.

Can AMD Instinct MI210 run ibm-granite/granite-docling-258M?

Runs Q464GB VRAM availableRequires 4GB+

AMD Instinct MI210 meets the minimum VRAM requirement for Q4 inference of ibm-granite/granite-docling-258M. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.

What this means for you

AMD Instinct MI210 can run ibm-granite/granite-docling-258M with Q4 quantization. At approximately 223 tokens/second, you can expect Excellent speed - conversational response times under 1 second.

You have 60GB headroom, which is sufficient for system overhead and smooth operation.

Quantization breakdown

QuantizationVRAM neededVRAM availableEstimated speedVerdict
Q44GB64GB223.10 tok/s✅ Fits comfortably
Q87GB64GB156.16 tok/s✅ Fits comfortably
FP1615GB64GB83.48 tok/s✅ Fits comfortably

Suitable alternatives

AMD Instinct MI300X
192GB
825.28 tok/s
Price: —
NVIDIA H200 SXM 141GB
141GB
685.38 tok/s
Price: —
AMD Instinct MI300X
192GB
515.48 tok/s
Price: —
AMD Instinct MI250X
128GB
507.39 tok/s
Price: —
NVIDIA H100 SXM5 80GB
80GB
506.43 tok/s
Price: —

More questions

AMD Instinct MI210 specs & pricingFull guide for ibm-granite/granite-docling-258Mibm-granite/granite-docling-258M speed on AMD Instinct MI210ibm-granite/granite-docling-258M Q4 requirements