Instructions to use FurAbyss/Equinox-31B-oQ4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use FurAbyss/Equinox-31B-oQ4 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Equinox-31B-oQ4 FurAbyss/Equinox-31B-oQ4
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,18 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
base_model:
|
| 4 |
+
- LatitudeGames/Equinox-31B
|
| 5 |
+
library_name: mlx
|
| 6 |
+
tags:
|
| 7 |
+
- oq
|
| 8 |
---
|
| 9 |
+
|
| 10 |
+
# Equinox-31B-oQ4
|
| 11 |
+
|
| 12 |
+
This model was quantized from [LatitudeGames/Equinox-31B](https://huggingface.co/LatitudeGames/Equinox-31B) using [oQ](https://github.com/jundot/omlx) (oMLX v0.3.8) mixed-precision quantization.
|
| 13 |
+
|
| 14 |
+
## Quantization details
|
| 15 |
+
- **Model type**: gemma4
|
| 16 |
+
- **Bits**: 4
|
| 17 |
+
- **Group size**: 64
|
| 18 |
+
- **Format**: MLX safetensors
|