roboflow · First MLX build 31 Mar 2026
rf-detr
MLX
Vision
A 39M parameter segmentation model from roboflow, with 5 MLX builds at fp32.
- Parameters
- 39M From Hugging Face
- Quantisation
- fp32 rfdetr-seg-small-fp32
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 135 MB Weights, estimated
- Downloads
- 32 This build, last 30 days
- Task
- Segmentation Vision
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 GB at fp32
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/rfdetr-seg-small-fp32MLX builds
5 on mlx-community| rfdetr-base-fp32 | fp32 | 129 MB | 3 GB | 25 |
|---|---|---|---|---|
| rfdetr-seg-small-fp32 | fp32 | 135 MB | 3 GB | 32 |
| rfdetr-seg-large-fp32 | fp32 | 145 MB | 3 GB | 28 |
| rfdetr-seg-xlarge-fp32 | fp32 | 152 MB | 3 GB | 25 |
| rfdetr-seg-2xlarge-fp32 | fp32 | 155 MB | 3 GB | 21 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.