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

Can Gemma 3 27B IT run on the Ryzen AI Max+ 395 128GB?

Yes. At 8K context the best fit is F16, using about 52.2 GB of the 109 GB usable on the Ryzen AI Max+ 395 128GB. Estimated speed ceiling: ~5 tokens/sec.

+ 0.8 GB with image input. The figures on this page are for text only. With image input enabled, the vision projector (mmproj) file loads alongside the model: F16 at 8K context then needs about 53.0 GB (still fits). llama.cpp's -hf downloads and loads it automatically unless you add --no-mmproj. Calculator with image input on.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •11.4 GB Fits11.7 GB Fits13.6 GB Fits21.1 GB Fits24
3-bit (Q3_K_M) •14.1 GB Fits14.4 GB Fits16.3 GB Fits23.8 GB Fits19
4-bit (Q4_K_M) •17.0 GB Fits17.3 GB Fits19.2 GB Fits26.7 GB Fits15
5-bit (Q5_K_M) •19.6 GB Fits19.9 GB Fits21.8 GB Fits29.3 GB Fits13
6-bit (Q6_K) •22.3 GB Fits22.6 GB Fits24.5 GB Fits32.0 GB Fits12
8-bit (Q8_0) •28.4 GB Fits28.7 GB Fits30.5 GB Fits38.0 GB Fits9
16-bit (F16/BF16) •51.9 GB Fits52.2 GB Fits54.1 GB Fits61.6 GB Fits5

• real GGUF file size from bartowski/google_gemma-3-27b-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

Gemma 3 27B 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/gemma-3-27b-it), AMD specs. Model data last checked 2026-11-18; refreshed hourly.