README.md

metadata

base_model: mistralai/Mistral-Large-Instruct-2407
language:
  - en
  - fr
  - de
  - es
  - it
  - pt
  - zh
  - ja
  - ru
  - ko
license: other
license_name: mrl
license_link: https://mistral.ai/licenses/MRL-0.1.md
pipeline_tag: text-generation
quantized_by: bartowski
extra_gated_description: >-
  If you want to learn more about how we process your personal data, please read
  our <a href="https://mistral.ai/terms/">Privacy Policy</a>.

Llamacpp imatrix Quantizations of Mistral-Large-Instruct-2407

Using llama.cpp release b3460 for quantization.

Original model: https://huggingface.co/mistralai/Mistral-Large-Instruct-2407

All quants made using imatrix option with dataset from here

Run them in LM Studio

Prompt format

<s>[INST] {prompt}[/INST] </s>

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

Filename	Quant type	File Size	Split	Description
Mistral-Large-Instruct-2407-Q8_0.gguf	Q8_0	130.28GB	true	Extremely high quality, generally unneeded but max available quant.
Mistral-Large-Instruct-2407-Q6_K.gguf	Q6_K	100.59GB	true	Very high quality, near perfect, recommended.
Mistral-Large-Instruct-2407-Q5_K_M.gguf	Q5_K_M	86.49GB	true	High quality, recommended.
Mistral-Large-Instruct-2407-Q5_K_S.gguf	Q5_K_S	84.36GB	true	High quality, recommended.
Mistral-Large-Instruct-2407-Q4_K_S.gguf	Q4_K_S	69.57GB	true	Slightly lower quality with more space savings, recommended.
Mistral-Large-Instruct-2407-Q3_K_XL.gguf	Q3_K_XL	64.91GB	true	Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability.
Mistral-Large-Instruct-2407-Q3_K_L.gguf	Q3_K_L	64.55GB	true	Lower quality but usable, good for low RAM availability.
Mistral-Large-Instruct-2407-Q2_K_L.gguf	Q2_K_L	45.59GB	false	Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable.

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/Mistral-Large-Instruct-2407-GGUF --include "Mistral-Large-Instruct-2407-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/Mistral-Large-Instruct-2407-GGUF --include "Mistral-Large-Instruct-2407-Q8_0.gguf/*" --local-dir Mistral-Large-Instruct-2407-Q8_0

You can either specify a new local-dir (Mistral-Large-Instruct-2407-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