Model comparison

bge-m3 vs nomic-embed-text-v2-moe

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

From the file· summed bytes, KV per layer

Side by side

bge-m3nomic-embed-text-v2-moe
Parameters567M475M
Architecturebertnomic-bert-moe
Layers2412
Native context8,194
Mixture of expertsnoyes, 8 experts
Quantizations published120
Smallest quantization0.59 GiB0.25 GiB
Q4_K_M0.32 GiB
Licencemitapache-2.0

KV cache by context

the term that decides long-context viability
Contextbge-m3nomic-embed-text-v2-moeRatio
4,0960.38 GiB
8,1920.75 GiB
16,3841.50 GiB
32,7683.00 GiB
65,5366.00 GiB
131,07212.00 GiB