All tasks / Models
nomic-embed-text-v2-moe
Nomic's Apache-2.0 multilingual mixture-of-experts text embedding model with open weights and data.
- Nomic AI
- Open weights
- Released Feb 2025
Where it ranks
- BEmbeddings & retrievalModels · Local · 57.6% on MTEB(Multilingual, v2)
Facts
- Vendor
- Nomic AI
- Family
- Nomic Embed Text
- Released
- Feb 2025
- Weights
- Open: download and run it yourself
- License
- Apache-2.0
- Parameters
- 0.48B
- GPU memory to run locally
- ~2 GB (Board lists ~1.8 GB memory use (0.48B parameters, fp32).)
- Access
- Free (open weights)
- Last verified
- 19 Oct 2026
Benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| MTEB(eng, v2) | 63.6% | nomic-ai/nomic-embed-text-v2-moeMean (Task) over all 41 tasks; board rank 99 (Borda); zero-shot share not declared on the board (-1); read from the leaderboard's public API. | 19 Oct 2026 | mteb-leaderboard-backend.hf.space |
| MTEB(Multilingual, v2) | 57.6% | nomic-ai/nomic-embed-text-v2-moeMean (Task) over all 131 tasks; board rank 55 (Borda); zero-shot share not declared on the board (-1); read from the leaderboard's public API. | 19 Oct 2026 | mteb-leaderboard-backend.hf.space |
Where you can use it
- SOllamaVector databases & engines · Local
- SText Embeddings InferenceVector databases & engines · Local
- SvLLMVector databases & engines · Local
Earlier versions
- nomic-embed-text-v1.5 · Feb 2024