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

Can Granite 4.0 H Tiny run on the Ryzen AI Max+ 395 128GB?

Yes. At 8K context the best fit is F16, using about 13.6 GB of the 109 GB usable on the Ryzen AI Max+ 395 128GB. Estimated speed ceiling: ~87 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •3.0 GB Fits3.1 GB Fits3.2 GB Fits4.0 GB Fits469
3-bit (Q3_K_M) •3.7 GB Fits3.8 GB Fits4.0 GB Fits4.7 GB Fits362
4-bit (Q4_K_M) •4.6 GB Fits4.6 GB Fits4.8 GB Fits5.5 GB Fits286
5-bit (Q5_K_M) •5.2 GB Fits5.3 GB Fits5.5 GB Fits6.2 GB Fits245
6-bit (Q6_K) •5.9 GB Fits6.0 GB Fits6.2 GB Fits6.9 GB Fits212
8-bit (Q8_0) •7.5 GB Fits7.5 GB Fits7.7 GB Fits8.5 GB Fits164
16-bit (F16/BF16) •13.6 GB Fits13.6 GB Fits13.8 GB Fits14.5 GB Fits87

• real GGUF file size from ibm-granite/granite-4.0-h-tiny-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 4.0 H Tiny 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-4.0-h-tiny), AMD specs. Model data last checked 2026-11-18; refreshed hourly.