nomic-embed-text-v1.5
Exciting Update!: nomic-embed-text-v1.5 is now multimodal! nomic-embed-vision-v1.5 is aligned to the embedding space of nomic-embed-text-v1.5, meaning any text embedding is multimodal!
Params
140 M
Context
2,048
Downloads 30d
15.7 M
Likes
885
Download history
daily snapshots · 10 days15.7 M14.8 M
Jul 28Jul 31Aug 3Aug 6
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | f32 | 0.5 GB | 1.1 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- NomicBertModel
- Parameters
- 140 M
- Tensor type
- F32
- Context length
- 2,048
- Vocabulary
- 30,528
- Layers / heads
- 12 / 12
- Licence
- apache-2.0
- First seen on the Hub
- 2024-02-10
- Training datasets
- undisclosed
- MTEB ArguAna (reported)
- 57.966
- MTEB BIOSSES (reported)
- 84.563975040309
- MTEB ArxivClusteringP2P (reported)
- 45.690695678511
- MTEB ArxivClusteringS2S (reported)
- 36.351854909763
- MTEB BiorxivClusteringP2P (reported)
- 38.770253446401
- MTEB BiorxivClusteringS2S (reported)
- 32.943070954973
- MTEB AskUbuntuDupQuestions (reported)
- 76.060326254232
- MTEB Banking77Classification (reported)
- 84.178722808926
- MTEB CQADupstackAndroidRetrieval (reported)
- 32.164
- MTEB AmazonPolarityClassification (reported)
- 91.804263016433
- MTEB AmazonReviewsClassification (en) (reported)
- 46.593296422632
- MTEB AmazonCounterfactualClassification (en) (reported)
- 69.355865658579
- Added to our catalog
- 2026-07-28
Compare with
Sponsored · GPU cloud
Not enough VRAM?
Spin up a 24 GB L4 instance in 40 seconds. $0.44/hr.