Model comparison

Qwen3.6-27B vs pagestorm-research-preview-14b-full-book

At Q4_K_M, pagestorm-research-preview-14b-full-book is the smaller download — 8,239,061,664 bytes against 16,547,397,888. At long context the gap widens: Qwen3.6-27B's KV cache at 32K is 2.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

Qwen3.6-27Bpagestorm-research-preview-14b-full-book
Parameters27.8B13.5B
Architectureqwen35mistral3
Layers6440
Native context262,144262,144
Mixture of expertsnono
Quantizations published402
Smallest quantization8.74 GiB7.67 GiB
Q4_K_M15.41 GiB7.67 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3.6-27Bpagestorm-research-preview-14b-full-bookRatio
4,0960.25 GiB0.63 GiB2.50×
8,1920.50 GiB1.25 GiB2.50×
16,3841.00 GiB2.50 GiB2.50×
32,7682.00 GiB5.00 GiB2.50×
65,5364.00 GiB10.00 GiB2.50×
131,0728.00 GiB20.00 GiB2.50×