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

Can DiffusionGemma 26B A4B IT run on the Ryzen AI Max+ 395 128GB?

Yes. At 8K context the best fit is F16, using about 48.5 GB of the 109 GB usable on the Ryzen AI Max+ 395 128GB. Estimated speed ceiling: ~33 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)10.3 GB Fits10.4 GB Fits11.4 GB Fits15.1 GB Fits171
3-bit (Q3_K_M)13.0 GB Fits13.2 GB Fits14.1 GB Fits17.8 GB Fits131
4-bit (Q4_K_M) •16.9 GB Fits17.1 GB Fits18.0 GB Fits21.7 GB Fits98
5-bit (Q5_K_M) •19.1 GB Fits19.2 GB Fits20.2 GB Fits23.9 GB Fits86
6-bit (Q6_K) •22.4 GB Fits22.5 GB Fits23.4 GB Fits27.2 GB Fits73
8-bit (Q8_0) •26.3 GB Fits26.4 GB Fits27.4 GB Fits31.1 GB Fits61
16-bit (F16/BF16) •48.3 GB Fits48.5 GB Fits49.4 GB Fits53.2 GB Fits33

• real GGUF file size from unsloth/diffusiongemma-26B-A4B-it-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

DiffusionGemma 26B A4B IT 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 (google/diffusiongemma-26B-A4B-it), AMD specs. Model data last checked 2026-11-18; refreshed hourly.