Model comparison

Qwen3.5-0.8B-Base vs Qwen3.5-0.8B

These two publish different quantization sets; the table below has the exact sizes.

From the file· summed bytes, KV per layer

Side by side

Qwen3.5-0.8B-BaseQwen3.5-0.8B
Parameters873M873M
Architectureqwen35qwen35
Layers2424
Native context262,144262,144
Mixture of expertsnono
Quantizations published342
Smallest quantization0.52 GiB0.31 GiB
Q4_K_M0.49 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3.5-0.8B-BaseQwen3.5-0.8BRatio
4,0960.05 GiB0.05 GiB1.00×
8,1920.09 GiB0.09 GiB1.00×
16,3840.19 GiB0.19 GiB1.00×
32,7680.38 GiB0.38 GiB1.00×
65,5360.75 GiB0.75 GiB1.00×
131,0721.50 GiB1.50 GiB1.00×