Is Mistral-7B-Instruct-v0.3-Jbliterated or Qwen3-8B smaller?

Mistral-7B-Instruct-v0.3-Jbliterated is smaller at Q4_K_M: 4.07 GiB against 4.68 GiB.

Which uses less memory at long context?

Mistral-7B-Instruct-v0.3-Jbliterated — its KV cache at 32K context is 1.1x smaller, because of how its attention layers cache.

Model comparison

At Q4_K_M, Mistral-7B-Instruct-v0.3-Jbliterated is the smaller download — 4,372,816,704 bytes against 5,027,783,488.

From the file· summed bytes, KV per layer

	Mistral-7B-Instruct-v0.3-Jbliterated	Qwen3-8B
Parameters	7.2B	8.2B
Architecture	llama	qwen3
Layers	32	36
Native context	32,768	40,960
Mixture of experts	no	no
Quantizations published	36	51
Smallest quantization	1.50 GiB	2.12 GiB
Q4_K_M	4.07 GiB	4.68 GiB
Licence	apache-2.0	apache-2.0

the term that decides long-context viability

Context	Mistral-7B-Instruct-v0.3-Jbliterated	Qwen3-8B	Ratio
4,096	0.50 GiB	0.56 GiB	1.13×
8,192	1.00 GiB	1.13 GiB	1.13×
16,384	2.00 GiB	2.25 GiB	1.13×
32,768	4.00 GiB	4.50 GiB	1.13×
65,536	8.00 GiB	9.00 GiB	1.13×
131,072	16.00 GiB	18.00 GiB	1.13×