Model comparison
Qwen3-Embedding-0.6B vs nomic-embed-text-v2-moe
At Q4_K_M, nomic-embed-text-v2-moe is the smaller download — 344,120,288 bytes against 396,474,560.
From the file· summed bytes, KV per layer
Side by side
| Qwen3-Embedding-0.6B | nomic-embed-text-v2-moe | |
|---|---|---|
| Parameters | 596M | 475M |
| Architecture | qwen3 | nomic-bert-moe |
| Layers | 28 | 12 |
| Native context | 32,768 | — |
| Mixture of experts | no | yes, 8 experts |
| Quantizations published | 22 | 20 |
| Smallest quantization | 0.28 GiB | 0.25 GiB |
| Q4_K_M | 0.37 GiB | 0.32 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | Qwen3-Embedding-0.6B | nomic-embed-text-v2-moe | 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 | — | — |