MLX Community · First MLX build 16 Sept 2026
Ornith-1.5-9B-oQ6e-mtp
MLX
A 9.7B parameter model, with one MLX build at 6-bit.
- Parameters
- 9.7B From Hugging Face
- Quantisation
- 6-bit Ornith-1.5-9B-oQ6e-mtp
- Memory needed
- 12 GB Estimate, unified memory
- Download
- 8.4 GB Weights, estimated
- Downloads
- 376 This build, last 30 days
- Task
- —
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 12 GB at 6-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/Ornith-1.5-9B-oQ6e-mtpMLX builds
1 on mlx-community| Ornith-1.5-9B-oQ6e-mtp | 6-bit | 8.4 GB | 12 GB | 376 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.