Can step3 run on the Ryzen AI Max+ 395 128GB?
No. Even at 2-bit with 8K context, step3 needs about 143 GB, more than the 109 GB usable on the Ryzen AI Max+ 395 128GB.
On this machine the GPU and CPU share one memory pool, so CPU offload does not add room. A smaller quant, a shorter context or more memory are the options.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|
| 2-bit (Q2_K) | 128 GB No | 143 GB No | 235 GB No | — |
| 3-bit (Q3_K_M) | 162 GB No | 177 GB No | 269 GB No | — |
| 4-bit (Q4_K_M) | 199 GB No | 214 GB No | 305 GB No | — |
| 5-bit (Q5_K_M) | 229 GB No | 244 GB No | 336 GB No | — |
| 6-bit (Q6_K) | 261 GB No | 276 GB No | 368 GB No | — |
| 8-bit (Q8_0) | 334 GB No | 349 GB No | 440 GB No | — |
| 16-bit (F16/BF16) | 614 GB No | 629 GB No | 720 GB No | — |
• real GGUF file size. Speed is a bandwidth ceiling (256 GB/s), not a benchmark. Methodology.
Hardware that does fit it
Mac M2 Ultra 192GBMac M3 Ultra 256GBMac M3 Ultra 512GB
What fits instead
- No listed GPU with a list price runs step3 fully in memory. The smallest listed hardware that does is the Mac M2 Ultra 192GB (192 GB).
- Largest popular model that fits the Ryzen AI Max+ 395 128GB: gpt-oss 120B (117B, MoE) at F16, about 61.9 GB at 8K context.
"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
step3 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/step3), AMD specs. Model data last checked 2026-11-18; refreshed hourly.