metadata
exported_from: xai-org/grok-1
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- grok-1
About
weighted/imatrix quants of https://huggingface.co/xai-org/grok-1
static quants are available at https://huggingface.co/mradermacher/grok-1-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 |
|---|---|---|---|
| PART 1 PART 2 | i1-IQ1_S | 66.7 | for the desperate |
| PART 1 PART 2 | i1-IQ1_M | 73.7 | for the desperate |
| PART 1 PART 2 | i1-IQ2_XXS | 85.4 | |
| PART 1 PART 2 | i1-IQ2_XS | 94.7 | |
| PART 1 PART 2 | i1-IQ2_S | 96.1 | |
| PART 1 PART 2 PART 3 | i1-IQ2_M | 105.4 | |
| PART 1 PART 2 PART 3 | i1-Q2_K | 117.2 | IQ3_XXS probably better |
| PART 1 PART 2 PART 3 | i1-IQ3_XXS | 123.7 | lower quality |
| PART 1 PART 2 PART 3 | i1-IQ3_XS | 130.7 | |
| PART 1 PART 2 PART 3 | i1-IQ3_S | 138.5 | beats Q3_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
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.