---
license: apache-2.0
tags:
- mixtral
- finetune
quantized_by: bartowski
pipeline_tag: text-generation
---

## Exllama v2 Quantizations of Smaug-Mixtral-v0.1

Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.13">turboderp's ExLlamaV2 v0.0.13</a> for quantization.

<b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>

Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.

Original model: https://huggingface.co/abacusai/Smaug-Mixtral-v0.1

| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
| ------ | ---- | ------------ | ---- | ---- | ---- | ----------- |
| [6_5](https://huggingface.co/bartowski/Smaug-Mixtral-v0.1-exl2/tree/6_5)   | 6.5  | 8.0 | 38.9 GB | 40.4 GB | 42.4 GB | Near unquantized performance at vastly reduced size, **recommended (if you can run it..)**.       |
| [4_25](https://huggingface.co/bartowski/Smaug-Mixtral-v0.1-exl2/tree/4_25) | 4.25 | 6.0 | 25.9 GB | 27.4 GB | 29.4 GB | GPTQ equivalent bits per weight, slightly higher quality.                   |
| [3_75](https://huggingface.co/bartowski/Smaug-Mixtral-v0.1-exl2/tree/3_75)   | 3.5  | 6.0 | 23.0 GB | 24.5 GB | 26.5 GB | Lower quality, but pretty usable. Good for 4k context on 24GB.            |
| [3_5](https://huggingface.co/bartowski/Smaug-Mixtral-v0.1-exl2/tree/3_5)   | 3.5  | 6.0 | 21.5 GB | 23.0 GB | 25.0 GB | Lower quality, only use if you need more context on 24GB.                   |
| [3_0](https://huggingface.co/bartowski/Smaug-Mixtral-v0.1-exl2/tree/3_0)   | 3.0  | 6.0 | 18.9 GB | 20.4 GB | 22.4 GB | Very low quality, pushes context to max but likely unusable.                |

## Download instructions

With git:

```shell
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Smaug-Mixtral-v0.1-exl2
```

With huggingface hub (credit to TheBloke for instructions):

```shell
pip3 install huggingface-hub
```

To download the `main` (only useful if you only care about measurement.json) branch to a folder called `Smaug-Mixtral-v0.1-exl2`:

```shell
mkdir Smaug-Mixtral-v0.1-exl2
huggingface-cli download bartowski/Smaug-Mixtral-v0.1-exl2 --local-dir Smaug-Mixtral-v0.1-exl2 --local-dir-use-symlinks False
```

To download from a different branch, add the `--revision` parameter:

Linux:

```shell
mkdir Smaug-Mixtral-v0.1-exl2-6_5
huggingface-cli download bartowski/Smaug-Mixtral-v0.1-exl2 --revision 6_5 --local-dir Smaug-Mixtral-v0.1-exl2-6_5 --local-dir-use-symlinks False
```

Windows (which apparently doesn't like _ in folders sometimes?):

```shell
mkdir Smaug-Mixtral-v0.1-exl2-6.5
huggingface-cli download bartowski/Smaug-Mixtral-v0.1-exl2 --revision 6_5 --local-dir Smaug-Mixtral-v0.1-exl2-6.5 --local-dir-use-symlinks False
```