Is Qwen3.8-27B or Mistral-Small-Drummer-22B smaller?

Mistral-Small-Drummer-22B is smaller at Q4_K_M: 12.43 GiB against 15.66 GiB.

Which uses less memory at long context?

Qwen3.8-27B — its KV cache at 32K context is 3.5x smaller, because of how its attention layers cache.

Model comparison

Qwen3.8-27B vs Mistral-Small-Drummer-22B

At Q4_K_M, Mistral-Small-Drummer-22B is the smaller download — 13,341,242,688 bytes against 16,810,714,336. At long context the gap widens: Qwen3.8-27B's KV cache at 32K is 3.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.8-27B	Mistral-Small-Drummer-22B
Parameters	27.8B	22.2B
Architecture	qwen35	llama
Layers	64	56
Native context	262,144	32,768
Mixture of experts	no	no
Quantizations published	22	22
Smallest quantization	8.39 GiB	6.19 GiB
Q4_K_M	15.66 GiB	12.43 GiB
Licence	apache-2.0	other

KV cache by context

the term that decides long-context viability

Context	Qwen3.8-27B	Mistral-Small-Drummer-22B	Ratio
4,096	0.25 GiB	0.88 GiB	3.50×
8,192	0.50 GiB	1.75 GiB	3.50×
16,384	1.00 GiB	3.50 GiB	3.50×
32,768	2.00 GiB	7.00 GiB	3.50×
65,536	4.00 GiB	14.00 GiB	3.50×
131,072	8.00 GiB	28.00 GiB	3.50×