Mixtral 8x22B V0.1 GGUF

🚀 Llamacpp Quantizations of Mixtral-8x22B-v0.1

This project provides quantized versions of the Mixtral-8x22B-v0.1 model using llama.cpp. It offers various quantization types to balance between model quality and resource requirements, making it suitable for different hardware setups.

🚀 Quick Start

The quantized models are generated using llama.cpp release b2636. The original model can be found at https://huggingface.co/mistral-community/Mixtral-8x22B-v0.1.

✨ Features

• Multiple Quantization Types: Offers a range of quantization types, including Q5_K_M, Q4_K_M, IQ4_NL, etc., to meet different quality and resource needs.
• Large Model Split: The large model is split into parts for easier upload and download. Recent versions of llamacpp can load the rest of the parts after loading part 1.

📦 Installation

There is no specific installation command provided in the original README. However, you can download the quantized model files from the links below according to your needs.

📚 Documentation

Prompt format

This is a base model with no prompt format.

Download a file (not the whole branch) from below

This is a very large model and has been split into parts to upload. Recent versions of llamacpp allow you to load part 1 and the rest will load as well. Make sure you download all parts of the chosen size.

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.

Support my work

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

📄 License

This project is licensed under the Apache-2.0 license.