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

Can Qwen3.8 27B run on the Ryzen AI Max+ 395 128GB?

Yes. At 8K context the best fit is F16, using about 52.3 GB of the 109 GB usable on the Ryzen AI Max+ 395 128GB. Estimated speed ceiling: ~5 tokens/sec.

+ 0.9 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 53.1 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) •11.2 GB Fits11.5 GB Fits13.0 GB Fits19.0 GB Fits24
3-bit (Q3_K_M) •13.6 GB Fits13.9 GB Fits15.4 GB Fits21.4 GB Fits19
4-bit (Q4_K_M) •17.4 GB Fits17.6 GB Fits19.1 GB Fits25.1 GB Fits15
5-bit (Q5_K_M) •20.6 GB Fits20.9 GB Fits22.4 GB Fits28.4 GB Fits12
6-bit (Q6_K) •23.3 GB Fits23.6 GB Fits25.1 GB Fits31.1 GB Fits11
8-bit (Q8_0) •28.2 GB Fits28.5 GB Fits30.0 GB Fits36.0 GB Fits9
16-bit (F16/BF16) •52.0 GB Fits52.3 GB Fits53.8 GB Fits59.8 GB Fits5

• real GGUF file size from bartowski/Qwen3.8-27B-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

Qwen3.8 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 (Qwen/Qwen3.8-27B), AMD specs. Model data last checked 2026-11-18; refreshed hourly.