Model comparison
embeddinggemma-300m-qat-q8_0-unquantized vs nomic-embed-text-v2-moe
These two publish different quantization sets; the table below has the exact sizes.
From the file· summed bytes, KV per layer
Side by side
| embeddinggemma-300m-qat-q8_0-unquantized | nomic-embed-text-v2-moe | |
|---|---|---|
| Parameters | 303M | 475M |
| Architecture | gemma-embedding | nomic-bert-moe |
| Layers | 24 | 12 |
| Native context | 2,048 | — |
| Mixture of experts | no | yes, 8 experts |
| Quantizations published | 1 | 20 |
| Smallest quantization | 0.31 GiB | 0.25 GiB |
| Q4_K_M | — | 0.32 GiB |
| Licence | gemma | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | embeddinggemma-300m-qat-q8_0-unquantized | nomic-embed-text-v2-moe | Ratio |
|---|---|---|---|
| 4,096 | 0.04 GiB | — | — |
| 8,192 | 0.05 GiB | — | — |
| 16,384 | 0.08 GiB | — | — |
| 32,768 | 0.14 GiB | — | — |
| 65,536 | 0.27 GiB | — | — |
| 131,072 | 0.52 GiB | — | — |