bf16 Open on Hugging Face
Parameters
1.1B
Weights (est.)
≈ 2.3 GB
Mac memory (est.)
8 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Details
- Base model
- nvidia/Nemotron-3-Embed-1B-BF16 (finetune)
- Vendor
- NVIDIA
- Task
- Sentence similarity
- Quantisation
- bf16
- Licence
- openmdw-1.1
- Downloads
- 203 in the last 30 days · 1.0K all time · 0 likes
- Published
- 2026-07-21 · updated 2026-08-04 (3mo ago)
- Languages
- en, ar, as, bn, bg, zh, da, nl, fi, fr, de, hi, id, it, ja, ko, ms, mr, ne, no, fa, pt, ro, ru, es, sw, sv, ta, te, th, uk, ur, vi, multilingual
- Tags
- ministral3, feature-extraction, retrieval, embeddings
Other MLX builds of nvidia/Nemotron-3-Embed-1B-BF16
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Nemotron-3-Embed-1B-BF16-4bit | 4-bit | ≈ 642 MB | 8 GB+ | 191 |
| Nemotron-3-Embed-1B-BF16-8bit | 8-bit | ≈ 1.2 GB | 8 GB+ | 267 |
| Nemotron-3-Embed-1B-BF16 (this one) | bf16 | ≈ 2.3 GB | 8 GB+ | 203 |