Instructions to use brainworkup/Ornith-1.0-9B-oQ8e with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use brainworkup/Ornith-1.0-9B-oQ8e with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Ornith-1.0-9B-oQ8e brainworkup/Ornith-1.0-9B-oQ8e
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Upload Ornith-1.0-9B-oQ8e via oMLX
Browse files
README.md
CHANGED
|
@@ -6,6 +6,10 @@ tags:
|
|
| 6 |
- quantized
|
| 7 |
---
|
| 8 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
# Ornith-1.0-9B-oQ8e
|
| 10 |
|
| 11 |
This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.5.4rc1) mixed-precision quantization.
|
|
|
|
| 6 |
- quantized
|
| 7 |
---
|
| 8 |
|
| 9 |
+
> [!IMPORTANT]
|
| 10 |
+
> This quantization was uploaded on **2026-08-01** and replaces a previous version.
|
| 11 |
+
> If you downloaded this model before this date, please re-download for the updated weights.
|
| 12 |
+
|
| 13 |
# Ornith-1.0-9B-oQ8e
|
| 14 |
|
| 15 |
This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.5.4rc1) mixed-precision quantization.
|