Steam Deck OLED · Gemma 4 31B · Q4_K_M
No. Gemma 4 31B at Q4_K_M does not fit on Steam Deck OLED at 8,192 tokens, even with 16 GB of system RAM.
| Piece | Value | Note |
|---|---|---|
| Weights | 17.1 GiB | gemma-4-31B-it-Q4_K_M.gguf |
| KV cache | 1.41 GiB | 8,192 tokens |
| Engine overhead | 0.50 GiB | Flat 0.5 GiB allowance |
| 5% headroom | 0.95 GiB | On the sum above |
| Total | 19.9 GiB | No |
| Fast memory | 12.0 GiB | After OS reserve |
| Speed | — | Dense bandwidth range |
ollama run gemma4:31b
Steam Deck OLED · Gemma 4 31B ·GGUF file · Methodology
FAQ
How was this fit calculated?
Weights 17.1 GiB, KV cache 1.41 GiB at 8,192 tokens, engine overhead 0.50 GiB, then 5% headroom, for 19.9 GiB. Fast memory available is 12.0 GiB.
What if I change the quant or the context?
This page is Q4_K_M at 8,192 tokens. A smaller quant or a shorter context lowers the total. The homepage calculator changes both without a new page.
Can I trust the tokens per second?
No speed is shown because the model does not load.
What do I type?
ollama run gemma4:31b
Is Steam Deck OLED assumed to have extra RAM?
No separate RAM pool. The chip's unified memory is the whole budget, minus the OS reserve described on the methodology page.