Model comparison

Qwen3.5-21B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking vs Qwen3.8-27B

At Q4_K_M, Qwen3.5-21B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking is the smaller download — 12,852,818,432 bytes against 16,810,714,336. At long context the gap widens: Qwen3.5-21B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking's KV cache at 32K is 1.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

Qwen3.5-21B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-ThinkingQwen3.8-27B
Parameters21.3B27.8B
Architectureqwen35qwen35
Layers4864
Native context262,144262,144
Mixture of expertsnono
Quantizations published3422
Smallest quantization5.30 GiB8.39 GiB
Q4_K_M11.97 GiB15.66 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3.5-21B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-ThinkingQwen3.8-27BRatio
4,0960.19 GiB0.25 GiB1.33×
8,1920.38 GiB0.50 GiB1.33×
16,3840.75 GiB1.00 GiB1.33×
32,7681.50 GiB2.00 GiB1.33×
65,5363.00 GiB4.00 GiB1.33×
131,0726.00 GiB8.00 GiB1.33×