File size: 229 Bytes
d66d895 |
1 2 3 4 5 6 |
---
base_model: nvidia/OpenReasoning-Nemotron-14B
---
[EXL3](https://github.com/turboderp-org/exllamav3) quantization of [OpenReasoning-Nemotron-14B](https://huggingface.co/nvidia/OpenReasoning-Nemotron-14B), 6 bits per weight.
|