Model comparison
cogito-v2-preview-deepseek-671B-MoE vs DeepSeek-V4-Flash-0731
These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: DeepSeek-V4-Flash-0731's KV cache at 32K is 34.0× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| cogito-v2-preview-deepseek-671B-MoE | DeepSeek-V4-Flash-0731 | |
|---|---|---|
| Parameters | 671B | 304B |
| Architecture | deepseek2 | deepseek4 |
| Layers | 61 | 43 |
| Native context | 163,840 | 1,048,576 |
| Mixture of experts | yes, 256 experts | yes, 256 experts |
| Quantizations published | 20 | 11 |
| Smallest quantization | 150.73 GiB | 76.87 GiB |
| Q4_K_M | 377.13 GiB | — |
| Licence | mit | mit |
KV cache by context
the term that decides long-context viability
| Context | cogito-v2-preview-deepseek-671B-MoE | DeepSeek-V4-Flash-0731 | Ratio |
|---|---|---|---|
| 4,096 | 0.27 GiB | 0.06 GiB | 4.26× |
| 8,192 | 0.54 GiB | 0.06 GiB | 8.51× |
| 16,384 | 1.07 GiB | 0.06 GiB | 17.02× |
| 32,768 | 2.14 GiB | 0.06 GiB | 34.05× |
| 65,536 | 4.29 GiB | 0.06 GiB | 68.09× |
| 131,072 | 8.58 GiB | 0.06 GiB | 136.19× |