Nemotron 3 Embed 1B BF16
Jul 2026
Nemotron 3 Embed 1B BF16Compare inon
Nemotron 3 Embed 1B BF16 measured on 22 of 261 Embeddings benchmarks22
BenchmarkByScoreRank
Reranking9
Other13
No benchmark matches
$0.015per 1M tokens
56.8RTEB French beta
Jul 2026released
2,048Dimensions
33K tokensMax input
en, es, fr +30Languages
Alternatives?
ModelScoreCostPriceWhat changes
CheaperQwen 3 Embedding 8BunstatedOpen+5%-33%$0.01Languages: not verified+1OpenNemotron 3 Embed 8B BF16+14%——Memory (4-bit): 0.7 GB → 4.8 GB
CheaperBge M3unstatedOpen-12%-33%$0.01Max input: 33K tokens → 8K tokens+1iCheaperMultilingual E5 LargeunstatedOpen-17%-33%$0.01Max input: 33K tokens → 1K tokensVBetterVoyage 4+7%+300%$0.06Max input: 33K tokens → 32K tokens+1ModelScoreCostPriceWhat changes
Qwen 3 Embedding 8BunstatedOpen+5%-33%$0.01Languages: not verified+1Bge M3unstatedOpen-12%-33%$0.01Max input: 33K tokens → 8K tokens+1iMultilingual E5 LargeunstatedOpen-17%-33%$0.01Max input: 33K tokens → 1K tokensModelScoreCostPriceWhat changes
Qwen 3 Embedding 8BunstatedOpen+5%-33%$0.01Languages: not verified+1VVoyage 4+7%+300%$0.06Max input: 33K tokens → 32K tokens+1VVoyage 4 Largeunstated+22%+700%$0.12Max input: 33K tokens → 32K tokens+1VVoyage 3 Large+7%+1,100%$0.18Max input: 33K tokens → 32K tokens+1Nemotron 3 Embed 8B BF16Open+14%——Memory (4-bit): 0.7 GB → 4.8 GBModelScoreCostPriceWhat changes
Nemotron 3 Embed 8B BF16Open+14%——Memory (4-bit): 0.7 GB → 4.8 GBOOcten Embedding 4BOpen+14%——Languages: loses es, fr, de +28+1OOcten Embedding 4B INT8Open+13%——Languages: loses es, fr, de +28+1NV Embed v2unstatedOpen+8%——Languages: loses es, fr, de +29+1OOcten Embedding 8BOpen+8%——Languages: loses es, fr, de +28+1Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · full quality✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
Licenceopenmdw-1.1commercial use with conditions
Benchmarks
in Embeddings & RetrievalMTEB German v1 · STS · German37.2#119
MTEB Dutch v1 · STS · Dutch45.8#129
FAQ
How much does Nemotron 3 Embed 1B BF16 cost?›
$0.015 per 1M tokens.
Is Nemotron 3 Embed 1B BF16 free to use?›
There is no free API; the cheapest paid price is $0.015 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Nemotron 3 Embed 1B BF16, and what is it best at?›
#18 of 212 in Embeddings.
Is Nemotron 3 Embed 1B BF16 better than Text Embedding 3 Large?›
On RTEB French beta · Mean over tasks · multilingual (2 languages), Nemotron 3 Embed 1B BF16 scores 56.8 vs 56.9 — about the same. It is 88% cheaper.
How can I use Nemotron 3 Embed 1B BF16?›
Through the NVIDIA API.
When was Nemotron 3 Embed 1B BF16 released? Is there a newer version?›
Released 2026-07-16. It is the current version in its line.
Is Nemotron 3 Embed 1B BF16 open source?›
Yes, the weights are open (openmdw-1.1 licence).
Can I run Nemotron 3 Embed 1B BF16 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Nemotron 3 Embed 1B BF16?›
Nemotron 3 Embed 1B BF16 is an open-weights embeddings & retrieval model from NVIDIA, released Jul 2026.
What are the best alternatives to Nemotron 3 Embed 1B BF16?›
Qwen 3 Embedding 8B (cheaper), Nemotron 3 Embed 8B BF16 (open weights).