Model comparison

Qwen3.5-9B-DFlash vs nomic-embed-text-v2-moe

At Q4_K_M, nomic-embed-text-v2-moe is the smaller download — 344,120,288 bytes against 765,959,872.

From the file· summed bytes, KV per layer

Side by side

Qwen3.5-9B-DFlashnomic-embed-text-v2-moe
Parameters1.3B475M
Architecturedflashnomic-bert-moe
Layers612
Native context262,144
Mixture of expertsnoyes, 8 experts
Quantizations published1120
Smallest quantization0.45 GiB0.25 GiB
Q4_K_M0.71 GiB0.32 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3.5-9B-DFlashnomic-embed-text-v2-moeRatio
4,0960.09 GiB
8,1920.12 GiB
16,3840.15 GiB
32,7680.21 GiB
65,5360.34 GiB
131,0720.59 GiB