Model comparison

FireRedPunc vs SmolLM-135M-Instruct

These two publish different quantization sets; the table below has the exact sizes.

From the file· summed bytes, KV per layer

Side by side

FireRedPuncSmolLM-135M-Instruct
Parameters102M135M
Architecturefireredpuncllama
Layers30
Native context2,048
Mixture of expertsnono
Quantizations published324
Smallest quantization0.05 GiB0.08 GiB
Q4_K_M0.10 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextFireRedPuncSmolLM-135M-InstructRatio
4,0960.09 GiB
8,1920.18 GiB
16,3840.35 GiB
32,7680.70 GiB
65,5361.41 GiB
131,0722.81 GiB