Model comparison

SmolLM2-135M-Instruct vs LFM2.5-350M

At Q4_K_M, SmolLM2-135M-Instruct is the smaller download — 105,454,144 bytes against 228,332,128. At long context the gap widens: LFM2.5-350M's KV cache at 32K is 1.9× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

SmolLM2-135M-InstructLFM2.5-350M
Parameters135M354M
Architecturellamalfm2
Layers3016
Native context8,192128,000
Mixture of expertsnono
Quantizations published4113
Smallest quantization0.08 GiB0.20 GiB
Q4_K_M0.10 GiB0.21 GiB
Licenceapache-2.0other

KV cache by context

the term that decides long-context viability
ContextSmolLM2-135M-InstructLFM2.5-350MRatio
4,0960.09 GiB0.05 GiB1.87×
8,1920.18 GiB0.09 GiB1.87×
16,3840.35 GiB0.19 GiB1.87×
32,7680.70 GiB0.38 GiB1.87×
65,5361.41 GiB0.75 GiB1.87×
131,0722.81 GiB1.50 GiB1.87×