Is command-r-35b-writer-v2 or gemma-4-E4B-it smaller?

gemma-4-E4B-it is smaller at Q4_K_M: 4.64 GiB against 20.05 GiB.

Which uses less memory at long context?

gemma-4-E4B-it — its KV cache at 32K context is 79.1x smaller, because of how its attention layers cache.

Model comparison

command-r-35b-writer-v2 vs gemma-4-E4B-it

At Q4_K_M, gemma-4-E4B-it is the smaller download — 4,977,171,584 bytes against 21,527,056,288. At long context the gap widens: gemma-4-E4B-it's KV cache at 32K is 79.1× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	command-r-35b-writer-v2	gemma-4-E4B-it
Parameters	35.0B	8.0B
Architecture	command-r	gemma4
Layers	40	42
Native context	8,192	131,072
Mixture of experts	no	no
Quantizations published	34	36
Smallest quantization	7.94 GiB	3.30 GiB
Q4_K_M	20.05 GiB	4.64 GiB
Licence	cc-by-nc-4.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	command-r-35b-writer-v2	gemma-4-E4B-it	Ratio
4,096	5.00 GiB	0.12 GiB	40.63×
8,192	10.00 GiB	0.18 GiB	56.26×
16,384	20.00 GiB	0.29 GiB	69.66×
32,768	40.00 GiB	0.51 GiB	79.07×
65,536	80.00 GiB	0.94 GiB	84.80×
131,072	160.00 GiB	1.82 GiB	87.99×