EXL3 quantization of gemma-3-12b-it, 4 bits per weight.
HumanEval (argmax)
| Model | Q4 | Q6 | Q8 | FP16 |
|---|---|---|---|---|
| gemma-3-12b-it-exl3-4bpw | 82.9 | 82.9 | 83.5 | 83.5 |
| gemma-3-12b-it-exl3-6bpw | 83.5 | 81.7 | 82.3 | 82.3 |
- Downloads last month
- 7
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support