Model comparison
jina-embeddings-v5-text-nano vs jina-embeddings-v5-text-small
At Q4_K_M, jina-embeddings-v5-text-nano is the smaller download — 156,966,976 bytes against 396,705,152. At long context the gap widens: jina-embeddings-v5-text-nano's KV cache at 32K is 3.1× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| jina-embeddings-v5-text-nano | jina-embeddings-v5-text-small | |
|---|---|---|
| Parameters | 212M | 596M |
| Architecture | eurobert | qwen3 |
| Layers | 12 | 28 |
| Native context | 8,192 | 32,768 |
| Mixture of experts | no | no |
| Quantizations published | 42 | 56 |
| Smallest quantization | 0.09 GiB | 0.19 GiB |
| Q4_K_M | 0.15 GiB | 0.37 GiB |
| Licence | cc-by-nc-4.0 | cc-by-nc-4.0 |
KV cache by context
the term that decides long-context viability
| Context | jina-embeddings-v5-text-nano | jina-embeddings-v5-text-small | Ratio |
|---|---|---|---|
| 4,096 | 0.14 GiB | 0.44 GiB | 3.11× |
| 8,192 | 0.28 GiB | 0.88 GiB | 3.11× |
| 16,384 | 0.56 GiB | 1.75 GiB | 3.11× |
| 32,768 | 1.13 GiB | 3.50 GiB | 3.11× |
| 65,536 | 2.25 GiB | 7.00 GiB | 3.11× |
| 131,072 | 4.50 GiB | 14.00 GiB | 3.11× |