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

Can Step 3.7 Flash run on the Ryzen AI Max+ 395 128GB?

Yes. At 8K context the best fit is Q3_K_M, using about 95.9 GB of the 109 GB usable on the Ryzen AI Max+ 395 128GB. Estimated speed ceiling: ~3 tokens/sec.

+ 3.7 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: Q3_K_M at 8K context then needs about 99.6 GB (tight). 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)73.0 GB Fits74.5 GB Fits83.5 GB Fits120 GB No3
3-bit (Q3_K_M)94.4 GB Fits95.9 GB Fits105 GB Tight141 GB No3
4-bit (Q4_K_M)117 GB No119 GB No128 GB No164 GB No—
5-bit (Q5_K_M)136 GB No138 GB No147 GB No183 GB No—
6-bit (Q6_K)156 GB No158 GB No167 GB No203 GB No—
8-bit (Q8_0)202 GB No203 GB No212 GB No248 GB No—
16-bit (F16/BF16)378 GB No379 GB No388 GB No424 GB No—

• 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

Step 3.7 Flash 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 (stepfun-ai/Step-3.7-Flash), AMD specs. Model data last checked 2026-11-18; refreshed hourly.