Model comparison
nomic-embed-text-v2-moe vs KaLM-embedding-multilingual-mini-instruct-v2.5
These two publish different quantization sets; the table below has the exact sizes.
From the file· summed bytes, KV per layer
Side by side
| nomic-embed-text-v2-moe | KaLM-embedding-multilingual-mini-instruct-v2.5 | |
|---|---|---|
| Parameters | 475M | 494M |
| Architecture | nomic-bert-moe | qwen2 |
| Layers | 12 | 24 |
| Native context | — | 131,072 |
| Mixture of experts | yes, 8 experts | no |
| Quantizations published | 20 | 1 |
| Smallest quantization | 0.25 GiB | 0.49 GiB |
| Q4_K_M | 0.32 GiB | — |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | nomic-embed-text-v2-moe | KaLM-embedding-multilingual-mini-instruct-v2.5 | Ratio |
|---|---|---|---|
| 4,096 | — | 0.05 GiB | — |
| 8,192 | — | 0.09 GiB | — |
| 16,384 | — | 0.19 GiB | — |
| 32,768 | — | 0.38 GiB | — |
| 65,536 | — | 0.75 GiB | — |
| 131,072 | — | 1.50 GiB | — |