Model comparison

Qwen3-0.6B-heretic-abliterated-uncensored vs MiniCPM5-1B-Claude-Opus-Fable5-Thinking

At Q4_K_M, Qwen3-0.6B-heretic-abliterated-uncensored is the smaller download — 396,705,312 bytes against 688,066,496. At long context the gap widens: MiniCPM5-1B-Claude-Opus-Fable5-Thinking's KV cache at 32K is 4.7× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

Qwen3-0.6B-heretic-abliterated-uncensoredMiniCPM5-1B-Claude-Opus-Fable5-Thinking
Parameters596M1.1B
Architectureqwen3llama
Layers2824
Native context40,960131,072
Mixture of expertsnono
Quantizations published3615
Smallest quantization0.19 GiB0.43 GiB
Q4_K_M0.37 GiB0.64 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3-0.6B-heretic-abliterated-uncensoredMiniCPM5-1B-Claude-Opus-Fable5-ThinkingRatio
4,0960.44 GiB0.09 GiB4.67×
8,1920.88 GiB0.19 GiB4.67×
16,3841.75 GiB0.38 GiB4.67×
32,7683.50 GiB0.75 GiB4.67×
65,5367.00 GiB1.50 GiB4.67×
131,07214.00 GiB3.00 GiB4.67×