Model comparison
DeepSeek-V4-Flash-Q8_0-GGUF 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
| DeepSeek-V4-Flash-Q8_0-GGUF | DeepSeek-V4-Flash | |
|---|---|---|
| Parameters | 284B | 291B |
| Architecture | deepseek4 | deepseek4 |
| Layers | — | 43 |
| Native context | — | 1,048,576 |
| Mixture of experts | no | yes, 256 experts |
| Quantizations published | 3 | 12 |
| Smallest quantization | 96.19 GiB | 76.87 GiB |
| Q4_K_M | 160.22 GiB | — |
| Licence | mit | mit |
KV cache by context
the term that decides long-context viability
| Context | DeepSeek-V4-Flash-Q8_0-GGUF | 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 | — |