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

Can Granite 4.1 3B run on the Ryzen AI Max+ 395 128GB?

Yes. At 8K context the best fit is F16, using about 7.6 GB of the 109 GB usable on the Ryzen AI Max+ 395 128GB. Estimated speed ceiling: ~38 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •2.2 GB Fits2.5 GB Fits4.4 GB Fits11.9 GB Fits187
3-bit (Q3_K_M) •2.5 GB Fits2.8 GB Fits4.7 GB Fits12.2 GB Fits148
4-bit (Q4_K_M) •2.9 GB Fits3.2 GB Fits5.0 GB Fits12.5 GB Fits122
5-bit (Q5_K_M) •3.2 GB Fits3.5 GB Fits5.4 GB Fits12.9 GB Fits105
6-bit (Q6_K) •3.5 GB Fits3.8 GB Fits5.7 GB Fits13.2 GB Fits92
8-bit (Q8_0) •4.3 GB Fits4.6 GB Fits6.5 GB Fits14.0 GB Fits71
16-bit (F16/BF16) •7.2 GB Fits7.6 GB Fits9.4 GB Fits16.9 GB Fits38

• real GGUF file size from ibm-granite/granite-4.1-3b-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

Granite 4.1 3B 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 (ibm-granite/granite-4.1-3b), AMD specs. Model data last checked 2026-11-18; refreshed hourly.