base_model: SaptivaAI/KAL-24B-mx-v1
datasets:
- SaptivaAI/kal-mx-training-data
language:
- es
library_name: transformers
license: apache-2.0
mradermacher:
readme_rev: 1
quantized_by: mradermacher
tags:
- text-generation
- finetuned
- instruct
- mistral
- mistral3
- 24b
- LoRA
- Saptiva AI
- KAL
- Mexico
- Spanish
- conversational
About
weighted/imatrix quants of https://huggingface.co/SaptivaAI/KAL-24B-mx-v1
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/KAL-24B-mx-v1-GGUF
Usage
If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.
Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|---|---|---|---|
| GGUF | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
| GGUF | i1-IQ2_M | 7.7 | |
| GGUF | i1-Q2_K_S | 7.8 | very low quality |
| GGUF | i1-Q2_K | 8.4 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 8.7 | lower quality |
| GGUF | i1-IQ3_M | 10.2 | |
| GGUF | i1-Q3_K_M | 10.9 | IQ3_S probably better |
| GGUF | i1-IQ4_XS | 12.0 | |
| GGUF | i1-Q4_K_S | 12.8 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 13.4 | fast, recommended |
| GGUF | i1-Q6_K | 18.4 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.
Thanks
I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.