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

Can Raon 1 Nano run on the Ryzen AI Max+ 395 128GB?

Yes. At 8K context the best fit is F16, using about 7.0 GB of the 109 GB usable on the Ryzen AI Max+ 395 128GB. Estimated speed ceiling: ~41 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)2.2 GB Fits2.3 GB Fits3.0 GB Fits5.5 GB Fits193
3-bit (Q3_K_M)2.6 GB Fits2.7 GB Fits3.3 GB Fits5.9 GB Fits148
4-bit (Q4_K_M) •2.9 GB Fits3.0 GB Fits3.7 GB Fits6.2 GB Fits123
5-bit (Q5_K_M)3.3 GB Fits3.4 GB Fits4.1 GB Fits6.6 GB Fits102
6-bit (Q6_K) •3.5 GB Fits3.6 GB Fits4.2 GB Fits6.7 GB Fits97
8-bit (Q8_0) •4.2 GB Fits4.3 GB Fits4.9 GB Fits7.4 GB Fits75
16-bit (F16/BF16) •6.8 GB Fits7.0 GB Fits7.6 GB Fits10.1 GB Fits41

• real GGUF file size from KRAFTON/Raon-1-nano-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

Raon 1 Nano 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 (KRAFTON/Raon-1-nano), AMD specs. Model data last checked 2026-11-18; refreshed hourly.