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

Can Phi 4 run on the Ryzen AI Max+ 395 128GB?

Yes. At 8K context the best fit is F16, using about 29.5 GB of the 109 GB usable on the Ryzen AI Max+ 395 128GB. Estimated speed ceiling: ~9 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •6.5 GB Fits7.3 GB Fits46
3-bit (Q3_K_M) •8.2 GB Fits9.0 GB Fits35
4-bit (Q4_K_M) •9.8 GB Fits10.6 GB Fits28
5-bit (Q5_K_M) •11.2 GB Fits12.0 GB Fits24
6-bit (Q6_K) •12.6 GB Fits13.4 GB Fits21
8-bit (Q8_0) •15.9 GB Fits16.7 GB Fits16
16-bit (F16/BF16) •28.7 GB Fits29.5 GB Fits9

• real GGUF file size from bartowski/phi-4-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

Phi 4 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 (microsoft/phi-4), AMD specs. Model data last checked 2026-11-18; refreshed hourly.