Is Olmo-3-7B-Think or Qwen3-8B smaller?

Olmo-3-7B-Think is smaller at Q4_K_M: 4.16 GiB against 4.68 GiB.

Which uses less memory at long context?

Qwen3-8B — its KV cache at 32K context is 1.3x smaller, because of how its attention layers cache.

Model comparison

Olmo-3-7B-Think vs Qwen3-8B

At Q4_K_M, Olmo-3-7B-Think is the smaller download — 4,471,600,192 bytes against 5,027,783,488. At long context the gap widens: Qwen3-8B's KV cache at 32K is 1.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Olmo-3-7B-Think	Qwen3-8B
Parameters	7.3B	8.2B
Architecture	olmo2	qwen3
Layers	32	36
Native context	65,536	40,960
Mixture of experts	no	no
Quantizations published	47	51
Smallest quantization	1.69 GiB	2.12 GiB
Q4_K_M	4.16 GiB	4.68 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Olmo-3-7B-Think	Qwen3-8B	Ratio
4,096	2.00 GiB	0.56 GiB	3.56×
8,192	2.69 GiB	1.13 GiB	2.39×
16,384	3.69 GiB	2.25 GiB	1.64×
32,768	5.69 GiB	4.50 GiB	1.26×
65,536	9.69 GiB	9.00 GiB	1.08×
131,072	17.69 GiB	18.00 GiB	1.02×