Model comparison
Qwen3.6-35B-A3B-DFlash vs ced-base
These two publish different quantization sets; the table below has the exact sizes.
From the file· summed bytes, KV per layer
Side by side
| Qwen3.6-35B-A3B-DFlash | ced-base | |
|---|---|---|
| Parameters | 386M | 86M |
| Architecture | dflash | ced |
| Layers | 6 | — |
| Native context | 262,144 | — |
| Mixture of experts | no | no |
| Quantizations published | 18 | 3 |
| Smallest quantization | 0.14 GiB | 0.12 GiB |
| Q4_K_M | 0.22 GiB | — |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | Qwen3.6-35B-A3B-DFlash | ced-base | Ratio |
|---|---|---|---|
| 4,096 | 0.09 GiB | — | — |
| 8,192 | 0.12 GiB | — | — |
| 16,384 | 0.15 GiB | — | — |
| 32,768 | 0.21 GiB | — | — |
| 65,536 | 0.34 GiB | — | — |
| 131,072 | 0.59 GiB | — | — |