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-DFlash | nomic-embed-text-v2-moe | |
|---|---|---|
| Parameters | 1.3B | 475M |
| Architecture | dflash | nomic-bert-moe |
| Layers | 6 | 12 |
| Native context | 262,144 | — |
| Mixture of experts | no | yes, 8 experts |
| Quantizations published | 11 | 20 |
| Smallest quantization | 0.45 GiB | 0.25 GiB |
| Q4_K_M | 0.71 GiB | 0.32 GiB |
| Licence | — | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | Qwen3.5-9B-DFlash | nomic-embed-text-v2-moe | Ratio |
|---|---|---|---|
| 4,096 | 0.09 GiB | — | — |
| 8,192 | 0.12 GiB | — | — |
| 16,384 | 0.15 GiB | — | — |
| 32,768 | 0.21 GiB | — | — |
| 65,536 | 0.34 GiB | — | — |
| 131,072 | 0.59 GiB | — | — |