Can Gemma 4 31B IT run on the Ryzen AI Max+ 395 128GB?
Yes. At 8K context the best fit is F16, using about 60.1 GB of the 109 GB usable on the Ryzen AI Max+ 395 128GB. Estimated speed ceiling: ~4 tokens/sec.
+ 1.1 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 61.2 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
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 14.1 GB Fits | 14.7 GB Fits | 18.4 GB Fits | 33.4 GB Fits | 20 |
| 3-bit (Q3_K_M) • | 17.1 GB Fits | 17.8 GB Fits | 21.5 GB Fits | 36.5 GB Fits | 16 |
| 4-bit (Q4_K_M) • | 20.6 GB Fits | 21.2 GB Fits | 24.9 GB Fits | 39.9 GB Fits | 13 |
| 5-bit (Q5_K_M) • | 23.4 GB Fits | 24.0 GB Fits | 27.7 GB Fits | 42.7 GB Fits | 11 |
| 6-bit (Q6_K) • | 27.2 GB Fits | 27.8 GB Fits | 31.6 GB Fits | 46.6 GB Fits | 10 |
| 8-bit (Q8_0) • | 32.7 GB Fits | 33.3 GB Fits | 37.1 GB Fits | 52.1 GB Fits | 8 |
| 16-bit (F16/BF16) • | 59.5 GB Fits | 60.1 GB Fits | 63.9 GB Fits | 78.9 GB Fits | 4 |
• real GGUF file size from bartowski/google_gemma-4-31B-it-GGUF. Speed is a bandwidth ceiling (256 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs Gemma 4 31B IT: RTX 5090 (32 GB, launch MSRP $1,999) at Q5_K_M, fully in VRAM at 8K context.
- Largest popular model that fits the Ryzen AI Max+ 395 128GB: gpt-oss 120B (117B, MoE) at F16, about 61.9 GB at 8K context.
"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 4 31B 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-4-31B-it), AMD specs. Model data last checked 2026-11-18; refreshed hourly.