Is Qwen3.8-27B or command-r-35b-writer-v2 smaller?

Qwen3.8-27B is smaller at Q4_K_M: 15.66 GiB against 20.05 GiB.

Which uses less memory at long context?

Qwen3.8-27B — its KV cache at 32K context is 20.0x smaller, because of how its attention layers cache.

Model comparison

Qwen3.8-27B vs command-r-35b-writer-v2

At Q4_K_M, Qwen3.8-27B is the smaller download — 16,810,714,336 bytes against 21,527,056,288. At long context the gap widens: Qwen3.8-27B's KV cache at 32K is 20.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.8-27B	command-r-35b-writer-v2
Parameters	27.8B	35.0B
Architecture	qwen35	command-r
Layers	64	40
Native context	262,144	8,192
Mixture of experts	no	no
Quantizations published	22	34
Smallest quantization	8.39 GiB	7.94 GiB
Q4_K_M	15.66 GiB	20.05 GiB
Licence	apache-2.0	cc-by-nc-4.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.8-27B	command-r-35b-writer-v2	Ratio
4,096	0.25 GiB	5.00 GiB	19.99×
8,192	0.50 GiB	10.00 GiB	19.99×
16,384	1.00 GiB	20.00 GiB	20.00×
32,768	2.00 GiB	40.00 GiB	20.00×
65,536	4.00 GiB	80.00 GiB	20.00×
131,072	8.00 GiB	160.00 GiB	20.00×