Llamacpp imatrix Quantizations of Llama-3-SEC-Chat

Using llama.cpp release b3166 for quantization.

Original model: https://huggingface.co/arcee-ai/Llama-3-SEC-Chat

All quants made using imatrix option with dataset from here

Prompt format

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

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

Filename Quant type File Size Description
Llama-3-SEC-Chat-Q8_0.gguf Q8_0 74.97GB Extremely high quality, generally unneeded but max available quant.
Llama-3-SEC-Chat-Q6_K.gguf Q6_K 57.88GB Very high quality, near perfect, recommended.
Llama-3-SEC-Chat-Q5_K_L.gguf Q5_K_L Experimental, uses f16 for embed and output weights. Please provide any feedback of differences. High quality, recommended.
Llama-3-SEC-Chat-Q5_K_M.gguf Q5_K_M 49.94GB High quality, recommended.
Llama-3-SEC-Chat-Q4_K_L.gguf Q4_K_L Experimental, uses f16 for embed and output weights. Please provide any feedback of differences. Good quality, uses about 4.83 bits per weight, recommended.
Llama-3-SEC-Chat-Q4_K_M.gguf Q4_K_M 42.52GB Good quality, uses about 4.83 bits per weight, recommended.
Llama-3-SEC-Chat-IQ4_XS.gguf IQ4_XS Decent quality, smaller than Q4_K_S with similar performance, recommended.
Llama-3-SEC-Chat-Q3_K_M.gguf Q3_K_M 34.26GB Even lower quality.
Llama-3-SEC-Chat-IQ3_M.gguf IQ3_M Medium-low quality, new method with decent performance comparable to Q3_K_M.
Llama-3-SEC-Chat-Q3_K_S.gguf Q3_K_S Low quality, not recommended.
Llama-3-SEC-Chat-IQ3_XXS.gguf IQ3_XXS Lower quality, new method with decent performance, comparable to Q3 quants.
Llama-3-SEC-Chat-Q2_K.gguf Q2_K 26.37GB Very low quality but surprisingly usable.
Llama-3-SEC-Chat-IQ2_M.gguf IQ2_M Very low quality, uses SOTA techniques to also be surprisingly usable.
Llama-3-SEC-Chat-IQ2_XS.gguf IQ2_XS Lower quality, uses SOTA techniques to be usable.
Llama-3-SEC-Chat-IQ2_XXS.gguf IQ2_XXS Lower quality, uses SOTA techniques to be usable.
Llama-3-SEC-Chat-IQ1_M.gguf IQ1_M Extremely low quality, not recommended.

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/Llama-3-SEC-Chat-GGUF --include "Llama-3-SEC-Chat-Q4_K_M.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/Llama-3-SEC-Chat-GGUF --include "Llama-3-SEC-Chat-Q8_0.gguf/*" --local-dir Llama-3-SEC-Chat-Q8_0

You can either specify a new local-dir (Llama-3-SEC-Chat-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 'QX_K_X', like Q5_K_M.

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 IQX_X, like IQ3_M. 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

Downloads last month
158
GGUF
Model size
70.6B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples
Unable to determine this model's library. Check the docs .

Space using arcee-ai/Llama-3-SEC-Chat-GGUF 1

Collection including arcee-ai/Llama-3-SEC-Chat-GGUF