base_model: DavidAU/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- Llama 3.2
- 8 X 3B
- 128k context
- moe
- 8 experts
- reasoning
- thinking
- r1
- cot
- deepseek
- mixture of experts
- mergekit
- merge
- llama-3
- llama-3.2
About
static quants of https://huggingface.co/DavidAU/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B
weighted/imatrix quants are available at https://huggingface.co/mradermacher/DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-i1-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 | Q2_K | 7.1 | |
| GGUF | Q3_K_S | 8.4 | |
| GGUF | Q3_K_M | 9.1 | lower quality |
| GGUF | Q3_K_L | 9.7 | |
| GGUF | IQ4_XS | 10.2 | |
| GGUF | Q4_K_S | 10.8 | fast, recommended |
| GGUF | Q4_K_M | 11.4 | fast, recommended |
| GGUF | Q5_K_S | 12.9 | |
| GGUF | Q5_K_M | 13.3 | |
| GGUF | Q6_K | 15.3 | very good quality |
| GGUF | Q8_0 | 19.7 | fast, best quality |
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.