NVIDIA · First MLX build 21 Jul 2026
Nemotron-3-Embed-1B-BF16
MLX
Text openmdw-1.1
A 1.1B parameter sentence similarity model from NVIDIA, with 3 MLX builds, from 4-bit to bf16.
- Parameters
- 1.1B From Hugging Face
- Quantisation
- 8-bit Nemotron-3-Embed-1B-BF16-8bit
- Memory needed
- 4 GB Estimate, unified memory
- Download
- 1.2 GB Weights, estimated
- Downloads
- 270 This build, last 30 days
- Task
- Sentence similarity Text
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 4 GB at 8-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/Nemotron-3-Embed-1B-BF16-8bitMLX builds
3 on mlx-community| Nemotron-3-Embed-1B-BF16-4bit | 4-bit | 642 MB | 3 GB | 193 |
|---|---|---|---|---|
| Nemotron-3-Embed-1B-BF16-8bit | 8-bit | 1.2 GB | 4 GB | 270 |
| Nemotron-3-Embed-1B-BF16 | bf16 | 2.3 GB | 5 GB | 200 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.