Yes — with 27.8 GB to spare
Gemma 4 31B at Q4_K_M fits your Ryzen AI Max+ 395 · 64 GB entirely in unified memory at 8K context, at an estimated 8.1 tokens per second. Past 185K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.
The dense flagship: strongest maths of the 24–32 GB class (89% AIME), clean prose, vision. Q4 is a tight 24 GB fit.
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 31.0 GB | 33.6 GB | 100K | 4.6 | −0.1% ppl | Long context |
| Q6_K | 23.9 GB | 26.5 GB | 145K | 6.0 | −0.4% ppl | Long context |
| Q5_K_M | 20.7 GB | 23.3 GB | 166K | 6.9 | −0.8% ppl | Long context |
| Q4_K_M | 17.6 GB | 20.2 GB | 185K | 8.1 | −1.9% ppl | Recommended |
| Q3_K_M | 14.2 GB | 16.9 GB | 207K | 10 | −5.4% ppl | Long context |
| Q2_K | 12.2 GB | 14.8 GB | 220K | 12 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. This model interleaves sliding-window layers (1024 tokens, 10 of 60 layers global), which is why its cache barely grows with context.
How to run it
$ ollama pull gemma4:31b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run gemma4:31b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.