Is MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking or gemma-3-1b-it smaller?

MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking is smaller at Q4_K_M: 0.64 GiB against 0.75 GiB.

Which uses less memory at long context?

gemma-3-1b-it — its KV cache at 32K context is 5.1x smaller, because of how its attention layers cache.

Model comparison

MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking vs gemma-3-1b-it

At Q4_K_M, MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking is the smaller download — 688,066,528 bytes against 806,058,240. At long context the gap widens: gemma-3-1b-it's KV cache at 32K is 5.1× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking	gemma-3-1b-it
Parameters	1.1B	1000M
Architecture	llama	gemma3
Layers	24	26
Native context	131,072	32,768
Mixture of experts	no	no
Quantizations published	10	28
Smallest quantization	0.64 GiB	0.52 GiB
Q4_K_M	0.64 GiB	0.75 GiB
Licence	apache-2.0	gemma

KV cache by context

the term that decides long-context viability

Context	MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking	gemma-3-1b-it	Ratio
4,096	0.09 GiB	0.04 GiB	2.53×
8,192	0.19 GiB	0.05 GiB	3.56×
16,384	0.38 GiB	0.08 GiB	4.47×
32,768	0.75 GiB	0.15 GiB	5.12×
65,536	1.50 GiB	0.27 GiB	5.53×
131,072	3.00 GiB	0.52 GiB	5.75×