Does gemma4-31B-Fable-5-Distilled fit in 12GB of VRAM?
Not at these settings. No indexed quantization of gemma4-31B-Fable-5-Distilled fits 12GB card at any context we compute, with q4_0 KV. The smallest shipped quantization is 30.39 GiB in weights alone, against 11.16 GiB usable. CPU offload can still run it, slowly.
Every quantization at every context
| Quant | Weights● | 4K◐ | 8K◐ | 16K◐ | 32K◐ | 64K◐ | 128K◐ |
|---|---|---|---|---|---|---|---|
| F16 | 57.20 GiB | 58.6 | 58.8 | 59.1 | 59.8 | 61.2 | 64.0 |
| Q8_0 | 30.39 GiB | 31.8 | 32.0 | 32.3 | 33.0 | 34.4 | 37.2 |
Figures are GiB of total memory: weights plus KV cache plus compute buffer and backend overhead. Weights and KV are near-exact; the overhead term is modeled. Hover any cell for the breakdown.
Why there are no speeds on this page
A capacity is not a card. Whether a model fits depends only on memory, so every figure above holds for any 12GB accelerator. How fast it runs depends on memory bandwidth, which varies several-fold between cards of the same capacity — so putting a tokens-per-second number here would be inventing one. Pick a specific card from hardware and the speed column appears.
Why other calculators disagree
A parameters × bits ÷ 8 estimate ignores two things that dominate at long context. First, the weights themselves are not the nominal rate — quantizations are mixtures, so the real file is consistently larger than the label implies. Second, most of this model's layers cache only a 1,024-token window rather than the full context.