| language: | |
| - eu | |
| pipeline_tag: text-generation | |
| tags: | |
| - gguf | |
| - latxa | |
| - 7b | |
| - hitz | |
| - llama | |
| - quant | |
| model_name: latxa-7b-v1 | |
| base_model: xezpeleta/latxa-7b-instruct | |
| # Latxa 7b Instruct GGUF | |
| ## Provided files | |
| | Name | Quant method | Bits | Size | Max RAM required | Use case | | |
| | ---- | ---- | ---- | ---- | ---- | ----- | | |
| | [latxa-7b-v1-instruct-q8_0.gguf](https://huggingface.co/oldbridge/latxa-7b-instruct-q8/blob/main/latxa-7b-instruct-q8.gguf) | |8 bits | 7 GB | 8,2 GB| Fits in a RTX 3060 12Gb | |