base_model: jiangchengchengNLP/Llama-4-Scout-17B-16E-Instruct-abliterated language:
- ar
- de
- en
- es
- fr
- hi
- id
- it
- pt
- th
- tl
- vi library_name: transformers license: llama4 mradermacher: readme_rev: 1 quantized_by: mradermacher tags:
- meta
- pytorch
- llama
- llama4
About
weighted/imatrix quants of https://huggingface.co/jiangchengchengNLP/Llama-4-Scout-17B-16E-Instruct-abliterated
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-abliterated-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 | i1-IQ1_S | 22.3 | for the desperate |
| GGUF | i1-IQ1_M | 24.7 | mostly desperate |
| GGUF | i1-IQ2_XXS | 28.7 | |
| GGUF | i1-IQ2_XS | 31.9 | |
| GGUF | i1-IQ2_S | 32.4 | |
| GGUF | i1-IQ2_M | 35.6 | |
| GGUF | i1-Q2_K_S | 37.1 | very low quality |
| GGUF | i1-Q2_K | 39.7 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 41.8 | lower quality |
| GGUF | i1-IQ3_XS | 44.4 | |
| GGUF | i1-Q3_K_S | 46.8 | IQ3_XS probably better |
| GGUF | i1-IQ3_S | 46.9 | beats Q3_K* |
| GGUF | i1-IQ3_M | 47.6 | |
| PART 1 PART 2 | i1-Q3_K_M | 51.9 | IQ3_S probably better |
| PART 1 PART 2 | i1-Q3_K_L | 56.1 | IQ3_M probably better |
| PART 1 PART 2 | i1-IQ4_XS | 57.7 | |
| PART 1 PART 2 | i1-Q4_0 | 61.3 | fast, low quality |
| PART 1 PART 2 | i1-Q4_K_S | 61.6 | optimal size/speed/quality |
| PART 1 PART 2 | i1-Q4_K_M | 65.5 | fast, recommended |
| PART 1 PART 2 | i1-Q4_1 | 67.7 | |
| PART 1 PART 2 | i1-Q5_K_S | 74.4 | |
| PART 1 PART 2 | i1-Q5_K_M | 76.6 | |
| PART 1 PART 2 | i1-Q6_K | 88.5 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
image.png
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.