Instructions to use g-oQ/Inkling-2-Mini-oQ2e with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use g-oQ/Inkling-2-Mini-oQ2e with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download g-oQ/Inkling-2-Mini-oQ2e --local-dir Inkling-2-Mini-oQ2e
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Inkling-2-Mini-oQ2e
This model was quantized using oQ (oMLX v0.8.2) mixed-precision quantization.
The effective average is 3.215 bits/weight for the complete checkpoint.
Quantization and Bit Distribution
| Storage format | Logical weights | Share of total | Tensor storage | Effective bits/weight |
|---|---|---|---|---|
| Affine 2-bit, group 64 | 24.461B | 91.592% | 7.119 GiB | 2.50 |
| Affine 8-bit, group 64 | 1.572B | 5.887% | 1.556 GiB | 8.50 |
| BF16 | 0.637B | 2.387% | 1.187 GiB | 16.00 |
| FP32 | 0.036B | 0.133% | 0.133 GiB | 32.00 |
| Total | 26.707B | 100% | 9.995 GiB | 3.215 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language model | 26.388B | 10.096 GB / 9.402 GiB |
| Vision | 0.318B | 0.637 GB / 0.593 GiB |
| Total | 26.707B | 10.732 GB / 9.995 GiB |
- Downloads last month
- -
Model size
26B params
Tensor type
U32
路
BF16 路
F32 路
Hardware compatibility
Log In to add your hardware
2-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support
Model tree for g-oQ/Inkling-2-Mini-oQ2e
Base model
thinkingmachines/Inkling-2-Mini