Is Huihui-MiniCPM5-1B-abliterated or Qwen3-1.7B smaller?

Huihui-MiniCPM5-1B-abliterated is smaller at Q4_K_M: 0.64 GiB against 1.03 GiB.

Which uses less memory at long context?

Huihui-MiniCPM5-1B-abliterated — its KV cache at 32K context is 4.7x smaller, because of how its attention layers cache.

Model comparison

Huihui-MiniCPM5-1B-abliterated vs Qwen3-1.7B

At Q4_K_M, Huihui-MiniCPM5-1B-abliterated is the smaller download — 688,067,040 bytes against 1,107,409,472. At long context the gap widens: Huihui-MiniCPM5-1B-abliterated'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

	Huihui-MiniCPM5-1B-abliterated	Qwen3-1.7B
Parameters	1.1B	2.0B
Architecture	llama	qwen3
Layers	24	28
Native context	131,072	40,960
Mixture of experts	no	no
Quantizations published	36	48
Smallest quantization	0.33 GiB	0.50 GiB
Q4_K_M	0.64 GiB	1.03 GiB
Licence	apache-2.0	—

KV cache by context

the term that decides long-context viability

Context	Huihui-MiniCPM5-1B-abliterated	Qwen3-1.7B	Ratio
4,096	0.09 GiB	0.44 GiB	4.67×
8,192	0.19 GiB	0.88 GiB	4.67×
16,384	0.38 GiB	1.75 GiB	4.67×
32,768	0.75 GiB	3.50 GiB	4.67×
65,536	1.50 GiB	7.00 GiB	4.67×
131,072	3.00 GiB	14.00 GiB	4.67×