Does Mellum2-12B-A2.5B-Thinking fit in 8GB of VRAM?
Not at these settings. No indexed quantization of Mellum2-12B-A2.5B-Thinking fits 8GB card at any context we compute, with q4_0 KV. The smallest shipped quantization is 7.52 GiB in weights alone, against 7.44 GiB usable. CPU offload can still run it, slowly.
Every quantization at every context
| Quant | Weights● | 4K◐ | 8K◐ | 16K◐ | 32K◐ | 64K◐ | 128K◐ |
|---|---|---|---|---|---|---|---|
| Q8_0 | 12.04 GiB | 12.9 | 12.9 | 12.9 | 13.0 | 13.1 | 13.3 |
| Q6_K | 10.13 GiB | 11.0 | 11.0 | 11.0 | 11.1 | 11.2 | 11.4 |
| Q4_K_M | 7.52 GiB | 8.3 | 8.4 | 8.4 | 8.5 | 8.6 | 8.8 |
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 8GB 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.