Model comparison

Qwen3.6-27B vs DeepSeek-R1-Distill-Qwen-32B-abliterated-v2

At Q4_K_M, Qwen3.6-27B is the smaller download — 16,547,397,888 bytes against 19,851,336,192.

From the file· summed bytes, KV per layer

Side by side

Qwen3.6-27BDeepSeek-R1-Distill-Qwen-32B-abliterated-v2
Parameters27.8B32.8B
Architectureqwen35qwen2
Layers64
Native context262,144
Mixture of expertsnono
Quantizations published4034
Smallest quantization8.74 GiB6.77 GiB
Q4_K_M15.41 GiB18.49 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3.6-27BDeepSeek-R1-Distill-Qwen-32B-abliterated-v2Ratio
4,0960.25 GiB
8,1920.50 GiB
16,3841.00 GiB
32,7682.00 GiB
65,5364.00 GiB
131,0728.00 GiB