Model comparison

Dolphin-Mistral-GLM-4.7-Flash-24B-Venice-Edition-Thinking-Uncensored vs Qwen3.8-27B

At Q4_K_M, Dolphin-Mistral-GLM-4.7-Flash-24B-Venice-Edition-Thinking-Uncensored is the smaller download — 14,333,910,688 bytes against 16,810,714,336. At long context the gap widens: Qwen3.8-27B'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

Dolphin-Mistral-GLM-4.7-Flash-24B-Venice-Edition-Thinking-UncensoredQwen3.8-27B
Parameters23.6B27.8B
Architecturellamaqwen35
Layers4064
Native context32,768262,144
Mixture of expertsnono
Quantizations published3422
Smallest quantization4.91 GiB8.39 GiB
Q4_K_M13.35 GiB15.66 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextDolphin-Mistral-GLM-4.7-Flash-24B-Venice-Edition-Thinking-UncensoredQwen3.8-27BRatio
4,0960.63 GiB0.25 GiB2.50×
8,1921.25 GiB0.50 GiB2.50×
16,3842.50 GiB1.00 GiB2.50×
32,7685.00 GiB2.00 GiB2.50×
65,53610.00 GiB4.00 GiB2.50×
131,07220.00 GiB8.00 GiB2.50×