RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Can MiniCPM5 2B run on the Ryzen AI Max+ 395 128GB?

Yes. At 8K context the best fit is F16, using about 5.7 GB of the 109 GB usable on the Ryzen AI Max+ 395 128GB. Estimated speed ceiling: ~51 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •1.8 GB Fits1.9 GB Fits2.9 GB Fits6.8 GB Fits252
3-bit (Q3_K_M) •2.0 GB Fits2.1 GB Fits3.1 GB Fits7.1 GB Fits207
4-bit (Q4_K_M) •2.3 GB Fits2.5 GB Fits3.5 GB Fits7.4 GB Fits158
5-bit (Q5_K_M) •2.6 GB Fits2.8 GB Fits3.7 GB Fits7.7 GB Fits133
6-bit (Q6_K) •2.8 GB Fits2.9 GB Fits3.9 GB Fits7.9 GB Fits121
8-bit (Q8_0) •3.3 GB Fits3.5 GB Fits4.5 GB Fits8.4 GB Fits96
16-bit (F16/BF16) •5.5 GB Fits5.7 GB Fits6.7 GB Fits10.6 GB Fits51

• real GGUF file size from bartowski/MiniCPM5-2B-GGUF. Speed is a bandwidth ceiling (256 GB/s), not a benchmark. Methodology.

What fits instead

"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.

More

MiniCPM5 2B on every GPU and Mac · Every model that runs on the Ryzen AI Max+ 395 128GB · Other models that fit 64 GB VRAM · Try other settings in the calculator

Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs

Data: Hugging Face Hub (openbmb/MiniCPM5-2B), AMD specs. Model data last checked 2026-11-18; refreshed hourly.