Model comparison
nomic-embed-text-v2-moe vs jina-embeddings-v5-text-small
At Q4_K_M, nomic-embed-text-v2-moe is the smaller download — 344,120,288 bytes against 396,705,152.
From the file· summed bytes, KV per layer
Side by side
| nomic-embed-text-v2-moe | jina-embeddings-v5-text-small | |
|---|---|---|
| Parameters | 475M | 596M |
| Architecture | nomic-bert-moe | qwen3 |
| Layers | 12 | 28 |
| Native context | — | 32,768 |
| Mixture of experts | yes, 8 experts | no |
| Quantizations published | 20 | 56 |
| Smallest quantization | 0.25 GiB | 0.19 GiB |
| Q4_K_M | 0.32 GiB | 0.37 GiB |
| Licence | apache-2.0 | cc-by-nc-4.0 |
KV cache by context
the term that decides long-context viability
| Context | nomic-embed-text-v2-moe | jina-embeddings-v5-text-small | Ratio |
|---|---|---|---|
| 4,096 | — | 0.44 GiB | — |
| 8,192 | — | 0.88 GiB | — |
| 16,384 | — | 1.75 GiB | — |
| 32,768 | — | 3.50 GiB | — |
| 65,536 | — | 7.00 GiB | — |
| 131,072 | — | 14.00 GiB | — |