Model comparison

gpt2 vs TinyMistral-248M-v2-Instruct

At Q4_K_M, gpt2 is the smaller download — 112,858,624 bytes against 155,668,768.

From the file· summed bytes, KV per layer

Side by side

gpt2TinyMistral-248M-v2-Instruct
Parameters137M248M
Architecturegpt2llama
Layers1212
Native context32,768
Mixture of expertsnono
Quantizations published496
Smallest quantization0.06 GiB0.10 GiB
Q4_K_M0.11 GiB0.14 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
Contextgpt2TinyMistral-248M-v2-InstructRatio
4,096
8,192
16,384
32,768
65,536
131,072