answerdotai · First MLX build 2 Apr 2025
ModernBERT-base
MLX
Text
A 149M parameter sentence similarity model from answerdotai, with 4 MLX builds, from 4-bit to bf16.
- Parameters
- 149M From Hugging Face
- Quantisation
- 4-bit tasksource-ModernBERT-base-embed-4bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 84 MB Weights, estimated
- Downloads
- 56 This build, last 30 days
- Task
- Sentence similarity Text
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 GB at 4-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/tasksource-ModernBERT-base-embed-4bitMLX builds
4 on mlx-community| tasksource-ModernBERT-base-embed-4bit | 4-bit | 84 MB | 3 GB | 56 |
|---|---|---|---|---|
| tasksource-ModernBERT-base-embed-6bit | 6-bit | 121 MB | 3 GB | 50 |
| tasksource-ModernBERT-base-embed-8bit | 8-bit | 158 MB | 3 GB | 46 |
| tasksource-ModernBERT-base-embed-bf16 | bf16 | 298 MB | 3 GB | 52 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.