Model comparison

Huihui-Qwen3.5-0.8B-abliterated 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

Huihui-Qwen3.5-0.8B-abliteratedced-base
Parameters873M86M
Architectureqwen35ced
Layers24
Native context262,144
Mixture of expertsnono
Quantizations published363
Smallest quantization0.27 GiB0.12 GiB
Q4_K_M0.49 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextHuihui-Qwen3.5-0.8B-abliteratedced-baseRatio
4,0960.05 GiB
8,1920.09 GiB
16,3840.19 GiB
32,7680.38 GiB
65,5360.75 GiB
131,0721.50 GiB