Is Mistral-Small-Instruct-2409 or Qwen3.8-27B smaller?

Mistral-Small-Instruct-2409 is smaller at Q4_K_M: 12.42 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

Mistral-Small-Instruct-2409 vs Qwen3.8-27B

At Q4_K_M, Mistral-Small-Instruct-2409 is the smaller download — 13,341,242,112 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

	Mistral-Small-Instruct-2409	Qwen3.8-27B
Parameters	22.2B	27.8B
Architecture	llama	qwen35
Layers	56	64
Native context	32,768	262,144
Mixture of experts	no	no
Quantizations published	52	22
Smallest quantization	4.50 GiB	8.39 GiB
Q4_K_M	12.42 GiB	15.66 GiB
Licence	—	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Mistral-Small-Instruct-2409	Qwen3.8-27B	Ratio
4,096	0.88 GiB	0.25 GiB	3.50×
8,192	1.75 GiB	0.50 GiB	3.50×
16,384	3.50 GiB	1.00 GiB	3.50×
32,768	7.00 GiB	2.00 GiB	3.50×
65,536	14.00 GiB	4.00 GiB	3.50×
131,072	28.00 GiB	8.00 GiB	3.50×