Is AMD-OLMo-1B-SFT-DPO or gemma-3-1b-it smaller?

AMD-OLMo-1B-SFT-DPO is smaller at Q4_K_M: 0.68 GiB against 0.75 GiB.

Which uses less memory at long context?

gemma-3-1b-it — its KV cache at 32K context is 27.3x smaller, because of how its attention layers cache.

Model comparison

AMD-OLMo-1B-SFT-DPO vs gemma-3-1b-it

At Q4_K_M, AMD-OLMo-1B-SFT-DPO is the smaller download — 733,520,640 bytes against 806,058,240. At long context the gap widens: gemma-3-1b-it's KV cache at 32K is 27.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	AMD-OLMo-1B-SFT-DPO	gemma-3-1b-it
Parameters	1.2B	1000M
Architecture	olmo	gemma3
Layers	16	26
Native context	2,048	32,768
Mixture of experts	no	no
Quantizations published	18	28
Smallest quantization	0.53 GiB	0.52 GiB
Q4_K_M	0.68 GiB	0.75 GiB
Licence	apache-2.0	gemma

KV cache by context

the term that decides long-context viability

Context	AMD-OLMo-1B-SFT-DPO	gemma-3-1b-it	Ratio
4,096	0.50 GiB	0.04 GiB	13.47×
8,192	1.00 GiB	0.05 GiB	18.96×
16,384	2.00 GiB	0.08 GiB	23.81×
32,768	4.00 GiB	0.15 GiB	27.31×
65,536	8.00 GiB	0.27 GiB	29.47×
131,072	16.00 GiB	0.52 GiB	30.68×