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 bigcode/starcoder2-3b?

Runs Q464GB VRAM availableRequires 2GB+

AMD Instinct MI210 meets the minimum VRAM requirement for Q4 inference of bigcode/starcoder2-3b. 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 bigcode/starcoder2-3b with Q4 quantization. At approximately 303 tokens/second, you can expect Excellent speed - conversational response times under 1 second.

You have 62GB headroom, which is sufficient for system overhead and smooth operation.

Quantization breakdown

QuantizationVRAM neededVRAM availableEstimated speedVerdict
Q42GB64GB302.81 tok/s✅ Fits comfortably
Q83GB64GB216.22 tok/s✅ Fits comfortably
FP166GB64GB111.69 tok/s✅ Fits comfortably

Suitable alternatives

AMD Instinct MI300X
192GB
974.08 tok/s
Price: —
NVIDIA H200 SXM 141GB
141GB
798.71 tok/s
Price: —
AMD Instinct MI300X
192GB
668.98 tok/s
Price: —
NVIDIA H200 SXM 141GB
141GB
591.63 tok/s
Price: —
AMD Instinct MI250X
128GB
570.73 tok/s
Price: —

More questions

AMD Instinct MI210 specs & pricingFull guide for bigcode/starcoder2-3bbigcode/starcoder2-3b speed on AMD Instinct MI210bigcode/starcoder2-3b Q4 requirements