Instructions to use brainworkup/Darwin-4B-David-oQ8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use brainworkup/Darwin-4B-David-oQ8 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Darwin-4B-David-oQ8 brainworkup/Darwin-4B-David-oQ8
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Upload Darwin-4B-David-oQ8 via oMLX
Browse files
README.md
CHANGED
|
@@ -6,13 +6,9 @@ tags:
|
|
| 6 |
- quantized
|
| 7 |
---
|
| 8 |
|
| 9 |
-
> [!IMPORTANT]
|
| 10 |
-
> This quantization was uploaded on **2026-06-16** and replaces a previous version.
|
| 11 |
-
> If you downloaded this model before this date, please re-download for the updated weights.
|
| 12 |
-
|
| 13 |
# Darwin-4B-David-oQ8
|
| 14 |
|
| 15 |
-
This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.
|
| 16 |
|
| 17 |
## Quantization details
|
| 18 |
|
|
|
|
| 6 |
- quantized
|
| 7 |
---
|
| 8 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
# Darwin-4B-David-oQ8
|
| 10 |
|
| 11 |
+
This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.5.4.dev1) mixed-precision quantization.
|
| 12 |
|
| 13 |
## Quantization details
|
| 14 |
|