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-DFlashced-base
Parameters386M86M
Architecturedflashced
Layers6
Native context262,144
Mixture of expertsnono
Quantizations published183
Smallest quantization0.14 GiB0.12 GiB
Q4_K_M0.22 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3.6-35B-A3B-DFlashced-baseRatio
4,0960.09 GiB
8,1920.12 GiB
16,3840.15 GiB
32,7680.21 GiB
65,5360.34 GiB
131,0720.59 GiB