base_model: DavidAU/DeepSeek-V2-Grand-Horror-SMB-R1-Distill-Llama-3.1-Uncensored-16.5B
language:
- en
library_name: transformers
quantized_by: mradermacher
tags: - mergekit
- merge
About
weighted/imatrix quants of https://huggingface.co/DavidAU/DeepSeek-V2-Grand-Horror-SMB-R1-Distill-Llama-3.1-Uncensored-16.5B
static quants are available at https://huggingface.co/mradermacher/DeepSeek-V2-Grand-Horror-SMB-R1-Distill-Llama-3.1-Uncensored-16.5B-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 | 3.9 | for the desperate |
| GGUF | i1-IQ1_M | 4.2 | mostly desperate |
| GGUF | i1-IQ2_XXS | 4.8 | |
| GGUF | i1-IQ2_XS | 5.2 | |
| GGUF | i1-IQ2_S | 5.5 | |
| GGUF | i1-IQ2_M | 5.9 | |
| GGUF | i1-Q2_K_S | 6.0 | very low quality |
| GGUF | i1-Q2_K | 6.4 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 6.6 | lower quality |
| GGUF | i1-IQ3_XS | 7.1 | |
| GGUF | i1-Q3_K_S | 7.4 | IQ3_XS probably better |
| GGUF | i1-IQ3_S | 7.5 | beats Q3_K* |
| GGUF | i1-IQ3_M | 7.7 | |
| GGUF | i1-Q3_K_M | 8.2 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 8.9 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 9.1 | |
| GGUF | i1-Q4_0 | 9.6 | fast, low quality |
| GGUF | i1-IQ4_NL | 9.6 | prefer IQ4_XS |
| GGUF | i1-Q4_K_S | 9.6 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 10.1 | fast, recommended |
| GGUF | i1-Q4_1 | 10.5 | |
| GGUF | i1-Q5_K_S | 11.5 | |
| GGUF | i1-Q5_K_M | 11.8 | |
| GGUF | i1-Q6_K | 13.7 | 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.