Model comparison

TinyMistral-248M-v2-Instruct vs Qwen3-0.6B

At Q4_K_M, TinyMistral-248M-v2-Instruct is the smaller download — 155,668,768 bytes against 396,705,472.

From the file· summed bytes, KV per layer

Side by side

TinyMistral-248M-v2-InstructQwen3-0.6B
Parameters248M752M
Architecturellamaqwen3
Layers1228
Native context32,76840,960
Mixture of expertsnono
Quantizations published644
Smallest quantization0.10 GiB0.20 GiB
Q4_K_M0.14 GiB0.37 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
ContextTinyMistral-248M-v2-InstructQwen3-0.6BRatio
4,0960.44 GiB
8,1920.88 GiB
16,3841.75 GiB
32,7683.50 GiB
65,5367.00 GiB
131,07214.00 GiB