Linzhan · First MLX build 14 Oct 2026
UniMate
MLX
cc-by-nc-4.0
A 184M parameter model from Linzhan, with 2 MLX builds at bf16.
- Parameters
- 184M From Hugging Face
- Quantisation
- bf16 unimate-uniml3d-f60-v3-bf16
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 367 MB Weights, estimated
- Downloads
- 52 This build, last 30 days
- Task
- —
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 GB at bf16
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/unimate-uniml3d-f60-v3-bf16MLX builds
2 on mlx-community| unimate-uniml3d-f60-v3-cross-attn-bf16 | bf16 | 352 MB | 3 GB | 36 |
|---|---|---|---|---|
| unimate-uniml3d-f60-v3-bf16 | bf16 | 367 MB | 3 GB | 52 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.