Model comparison
MiMo-V2.5 vs DeepSeek-V4-Flash
These two publish different quantization sets; the table below has the exact sizes.
From the file· summed bytes, KV per layer
Side by side
| MiMo-V2.5 | DeepSeek-V4-Flash | |
|---|---|---|
| Parameters | 311B | 291B |
| Architecture | mimo2 | deepseek4 |
| Layers | 48 | 43 |
| Native context | 1,048,576 | 1,048,576 |
| Mixture of experts | yes, 256 experts | yes, 256 experts |
| Quantizations published | 44 | 12 |
| Smallest quantization | 60.09 GiB | 76.87 GiB |
| Q4_K_M | 175.80 GiB | — |
| Licence | mit | mit |
KV cache by context
the term that decides long-context viability
| Context | MiMo-V2.5 | DeepSeek-V4-Flash | Ratio |
|---|---|---|---|
| 4,096 | — | 0.06 GiB | — |
| 8,192 | — | 0.06 GiB | — |
| 16,384 | — | 0.06 GiB | — |
| 32,768 | — | 0.06 GiB | — |
| 65,536 | — | 0.06 GiB | — |
| 131,072 | — | 0.06 GiB | — |