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

Can HunyuanOCR run on the Ryzen AI Max+ 395 128GB?

Yes. At 8K context the best fit is F16, using about 3.5 GB of the 109 GB usable on the Ryzen AI Max+ 395 128GB. Estimated speed ceiling: ~114 tokens/sec.

+ 0.7 GB with image input. The figures on this page are for text only. With image input enabled, the vision projector (mmproj) file loads alongside the model: F16 at 8K context then needs about 4.1 GB (still fits). llama.cpp's -hf downloads and loads it automatically unless you add --no-mmproj. Calculator with image input on.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)1.4 GB Fits1.8 GB Fits4.0 GB Fits13.0 GB Fits610
3-bit (Q3_K_M)1.5 GB Fits1.9 GB Fits4.1 GB Fits13.1 GB Fits468
4-bit (Q4_K_M)1.6 GB Fits2.0 GB Fits4.3 GB Fits13.3 GB Fits374
5-bit (Q5_K_M)1.7 GB Fits2.1 GB Fits4.4 GB Fits13.4 GB Fits321
6-bit (Q6_K)1.9 GB Fits2.2 GB Fits4.5 GB Fits13.5 GB Fits279
8-bit (Q8_0)2.1 GB Fits2.5 GB Fits4.7 GB Fits13.7 GB Fits215
16-bit (F16/BF16)3.1 GB Fits3.5 GB Fits5.7 GB Fits14.7 GB Fits114

• real GGUF file size. 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

HunyuanOCR 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 (tencent/HunyuanOCR), AMD specs. Model data last checked 2026-11-18; refreshed hourly.