Alternatives to Octen-Embedding-4B
Octen-Embedding-4B alternatives
Octen-Embedding-4B's smallest published quantization is 1.55 GiB. The models below do the same job with a different trade — less memory, comparable size, or a more permissive licence.
From the file· sizes from summed file bytes
Meaningfully smaller
under 70% of its smallest quantization
| Model | Params | Smallest | Quants | Licence |
|---|---|---|---|---|
| jina-embeddings-v5-text-small | 596M | 0.19 GiB | 56 | cc-by-nc-4.0 |
| embeddinggemma-300m-qat-q8_0-unquantized | 303M | 0.31 GiB | 1 | gemma |
| KaLM-embedding-multilingual-mini-instruct-v2.5 | 494M | 0.49 GiB | 1 | apache-2.0 |
| nomic-embed-text-v1.5 | 137M | 0.05 GiB | 39 | apache-2.0 |
| jina-embeddings-v5-text-nano | 212M | 0.09 GiB | 42 | cc-by-nc-4.0 |
| all-MiniLM-L6-v2 | 23M | 0.02 GiB | 28 | apache-2.0 |
| mxbai-embed-xsmall-v1 | 24M | 0.03 GiB | 4 | apache-2.0 |
| nomic-embed-text-v2-moeMoE | 475M | 0.25 GiB | 20 | apache-2.0 |
Comparable in size
within ±40%, so a like-for-like swap
| Model | Params | Smallest | Quants | Licence |
|---|---|---|---|---|
| Qwen3-Embedding-4B | 4.0B | 1.55 GiB | 18 | apache-2.0 |
| Nemotron-3-Embed-8B-BF16 | 8.0B | 1.81 GiB | 36 | openmdw-1.1 |
| LCO-Embedding-Omni-3B-2605 | 4.7B | 1.96 GiB | 4 | apache-2.0 |
| qwen-indic-v1 | 7.6B | 1.78 GiB | 36 | apache-2.0 |
More permissively licensed
licences that allow commercial use
| Model | Params | Smallest | Quants | Licence |
|---|---|---|---|---|
| KaLM-embedding-multilingual-mini-instruct-v2.5 | 494M | 0.49 GiB | 1 | apache-2.0 |
| nomic-embed-text-v1.5 | 137M | 0.05 GiB | 39 | apache-2.0 |
| all-MiniLM-L6-v2 | 23M | 0.02 GiB | 28 | apache-2.0 |
| mxbai-embed-xsmall-v1 | 24M | 0.03 GiB | 4 | apache-2.0 |
| nomic-embed-text-v2-moeMoE | 475M | 0.25 GiB | 20 | apache-2.0 |
| bge-m3 | 567M | 0.59 GiB | 1 | mit |
| jina-reranker-v1-tiny-en | 33M | 0.03 GiB | 12 | apache-2.0 |
| Qwen3-Embedding-0.6B | 596M | 0.28 GiB | 22 | apache-2.0 |