Model comparison

bitnet_b1_58-large vs ced-base

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

From the file· summed bytes, KV per layer

Side by side

bitnet_b1_58-largeced-base
Parameters729M86M
Architecturebitnetced
Layers24
Native context2,048
Mixture of expertsnono
Quantizations published13
Smallest quantization0.20 GiB0.12 GiB
Q4_K_M
Licencemitapache-2.0

KV cache by context

the term that decides long-context viability
Contextbitnet_b1_58-largeced-baseRatio
4,0960.56 GiB
8,1921.13 GiB
16,3842.25 GiB
32,7684.50 GiB
65,5369.00 GiB
131,07218.00 GiB