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

Can Arete 27B run on the Ryzen AI Max+ 395 128GB?

Yes. At 8K context the best fit is F16, using about 51.5 GB of the 109 GB usable on the Ryzen AI Max+ 395 128GB. Estimated speed ceiling: ~5 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •11.0 GB Fits11.2 GB Fits12.7 GB Fits18.7 GB Fits24
3-bit (Q3_K_M) •13.4 GB Fits13.6 GB Fits15.1 GB Fits21.1 GB Fits19
4-bit (Q4_K_M) •17.1 GB Fits17.4 GB Fits18.9 GB Fits24.9 GB Fits15
5-bit (Q5_K_M) •20.4 GB Fits20.6 GB Fits22.1 GB Fits28.1 GB Fits12
6-bit (Q6_K) •23.1 GB Fits23.4 GB Fits24.9 GB Fits30.9 GB Fits11
8-bit (Q8_0) •27.8 GB Fits28.1 GB Fits29.6 GB Fits35.6 GB Fits9
16-bit (F16/BF16) •51.2 GB Fits51.5 GB Fits53.0 GB Fits59.0 GB Fits5

• real GGUF file size from bartowski/NousResearch_Arete-27B-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

Arete 27B 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 (NousResearch/Arete-27B), AMD specs. Model data last checked 2026-11-18; refreshed hourly.