Model comparison
DeepSeek-V4-Flash vs Mistral-Large-3-675B-Instruct-2512
These two publish different quantization sets; the table below has the exact sizes.
From the file· summed bytes, KV per layer
Side by side
| DeepSeek-V4-Flash | Mistral-Large-3-675B-Instruct-2512 | |
|---|---|---|
| Parameters | 291B | 673B |
| Architecture | deepseek4 | deepseek2 |
| Layers | 43 | — |
| Native context | 1,048,576 | — |
| Mixture of experts | yes, 256 experts | no |
| Quantizations published | 12 | 45 |
| Smallest quantization | 76.87 GiB | 132.50 GiB |
| Q4_K_M | — | 379.04 GiB |
| Licence | mit | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | DeepSeek-V4-Flash | Mistral-Large-3-675B-Instruct-2512 | 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 | — | — |