bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF

---

base_model: aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored language:

• en
• de
• fr
• it
• pt
• hi
• es
• th
• zh
• ko
• ja

license: llama3.1 pipeline_tag: text-generation tags:

• roleplay
• llama3
• sillytavern
• idol
• facebook
• meta
• pytorch
• llama
• llama-3

quantized_by: bartowski extragatedfields: First Name: text Last Name: text Date of birth: date_picker Country: country Affiliation: text Job title: type: select options: - Student - Research Graduate - AI researcher - AI developer/engineer - Reporter - Other

---

Llamacpp imatrix Quantizations of DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored

Using llama.cpp release b3496 for quantization.

Original model: https://huggingface.co/aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored

All quants made using imatrix option with dataset from here

Run them in LM Studio

Prompt format

<|beginoftext|><|startheaderid|>system<|endheaderid|>

{systemprompt}<|eotid|><|startheaderid|>user<|endheaderid|>

{prompt}<|eotid|><|startheaderid|>assistant<|endheader_id|>

<|eot_id|>

Download a file (not the whole branch) from below:

Filename	Quant type	File Size	Split	Description
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-f32.gguf	f32	32.13GB	false	Full F32 weights.
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q80.gguf	Q80	8.54GB	false	Extremely high quality, generally unneeded but max available quant.
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q6KL.gguf	Q6KL	6.85GB	false	Uses Q80 for embed and output weights. Very high quality, near perfect, recommended.
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q6K.gguf	Q6K	6.60GB	false	Very high quality, near perfect, recommended.
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q5KL.gguf	Q5KL	6.06GB	false	Uses Q80 for embed and output weights. High quality, recommended.
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q5KM.gguf	Q5K_M	5.73GB	false	High quality, recommended.
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q5KS.gguf	Q5K_S	5.60GB	false	High quality, recommended.
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q4KL.gguf	Q4KL	5.31GB	false	Uses Q80 for embed and output weights. Good quality, recommended.
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q4KM.gguf	Q4K_M	4.92GB	false	Good quality, default size for must use cases, recommended.
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q3KXL.gguf	Q3KXL	4.78GB	false	Uses Q80 for embed and output weights. Lower quality but usable, good for low RAM availability.
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q4KS.gguf	Q4K_S	4.69GB	false	Slightly lower quality with more space savings, recommended.
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-IQ4XS.gguf	IQ4XS	4.45GB	false	Decent quality, smaller than Q4KS with similar performance, recommended.
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q3KL.gguf	Q3K_L	4.32GB	false	Lower quality but usable, good for low RAM availability.
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q3KM.gguf	Q3K_M	4.02GB	false	Low quality.
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-IQ3M.gguf	IQ3M	3.78GB	false	Medium-low quality, new method with decent performance comparable to Q3KM.
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q2KL.gguf	Q2KL	3.69GB	false	Uses Q80 for embed and output weights. Very low quality but surprisingly usable.
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q3KS.gguf	Q3K_S	3.66GB	false	Low quality, not recommended.
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-IQ3XS.gguf	IQ3XS	3.52GB	false	Lower quality, new method with decent performance, slightly better than Q3KS.
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q2K.gguf	Q2K	3.18GB	false	Very low quality but surprisingly usable.
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-IQ2M.gguf	IQ2M	2.95GB	false	Relatively low quality, uses SOTA techniques to be surprisingly usable.

Embed/output weights

Some of these quants (Q3KXL, Q4KL etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.

Some say that this improves the quality, others don't notice any difference. If you use these models PLEASE COMMENT with your findings. I would like feedback that these are actually used and useful so I don't keep uploading quants no one is using.

Thanks!

Credits

Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset

Thank you ZeroWw for the inspiration to experiment with embed/output

Downloading using huggingface-cli

First, make sure you have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Then, you can target the specific file you want:

huggingface-cli download bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF --include "DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q4KM.gguf" --local-dir ./

If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF --include "DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q8_0/*" --local-dir ./

You can either specify a new local-dir (DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q8_0) or download them all in place (./)

Which file should I choose?

A great write up with charts showing various performances is provided by Artefact2 here

The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.

If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.

If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.

Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.

If you don't want to think too much, grab one of the K-quants. These are in format 'QXKX', like Q5KM.

If you want to get more into the weeds, you can check out this extremely useful feature chart:

llama.cpp feature matrix

But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQXX, like IQ3M. These are newer and offer better performance for their size.

These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.

The I-quants are not compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski