MLX Community · First MLX build 2 Apr 2025
answerdotai-ModernBERT-Large-Instruct
MLX
Text apache-2.0
A 447M parameter fill mask model, with 4 MLX builds, from 4-bit to bf16.
- Parameters
- 447M From Hugging Face
- Quantisation
- 4-bit answerdotai-ModernBERT-Large-Instruct-4bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 252 MB Weights, estimated
- Downloads
- 29 This build, last 30 days
- Task
- Fill mask 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/answerdotai-ModernBERT-Large-Instruct-4bitMLX builds
4 on mlx-community| answerdotai-ModernBERT-Large-Instruct-4bit | 4-bit | 252 MB | 3 GB | 29 |
|---|---|---|---|---|
| answerdotai-ModernBERT-Large-Instruct-6bit | 6-bit | 364 MB | 3 GB | 11 |
| answerdotai-ModernBERT-Large-Instruct-8bit | 8-bit | 476 MB | 3 GB | 14 |
| answerdotai-ModernBERT-Large-Instruct-bf16 | bf16 | 895 MB | 4 GB | 7 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.