---
inference: false
license: other
license_name: mnpl
license_link: https://mistral.ai/licences/MNPL-0.1.md
tags:
- code
language:
- code
quantized_by: bartowski
pipeline_tag: text-generation
---

## Exllama v2 Quantizations of Codestral-22B-v0.1

Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.1.1">turboderp's ExLlamaV2 v0.1.1</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/mistral-community/Codestral-22B-v0.1

## Prompt format

No chat template specified so default is used. This may be incorrect, check original model card for details.

```
<s> [INST] <<SYS>>
{system_prompt}
<</SYS>>

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

## Available sizes

| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
| ------ | ---- | ------------ | ---- | ---- | ---- | ----------- |
| [8_0](https://huggingface.co/bartowski/Codestral-22B-v0.1-exl2/tree/8_0)   | 8.0  | 8.0 | 23.5 GB | 26.0 GB | 29.5 GB | Near unquantized performance, max quality ExLlamaV2 can create.     |
| [6_5](https://huggingface.co/bartowski/Codestral-22B-v0.1-exl2/tree/6_5)   | 6.5  | 8.0 | 19.4 GB | 21.9 GB | 25.4 GB | Near unquantized performance at vastly reduced size, **recommended**.       |
| [5_0](https://huggingface.co/bartowski/Codestral-22B-v0.1-exl2/tree/5_0)   | 5.0  | 6.0 | 15.5 GB | 18.0 GB | 21.5 GB | Smaller size, lower quality, still very high performance, **recommended**.       |
| [4_25](https://huggingface.co/bartowski/Codestral-22B-v0.1-exl2/tree/4_25) | 4.25 | 6.0 | 13.3 GB | 15.8 GB | 19.3 GB | GPTQ equivalent bits per weight, slightly higher quality.                   |
| [3_5](https://huggingface.co/bartowski/Codestral-22B-v0.1-exl2/tree/3_5)   | 3.5  | 6.0 | 11.6 GB | 14.1 GB | 17.6 GB | Lower quality, only use if you have to.                                     |
| [3_0](https://huggingface.co/bartowski/Codestral-22B-v0.1-exl2/tree/3_0)   | 3.0  | 6.0 | 9.8 GB | 12.3 GB | 15.8 GB | Very low quality. Usable on 12GB with low context or 16gb with 32k. |

## Download instructions

With git:

```shell
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Codestral-22B-v0.1-exl2 Codestral-22B-v0.1-exl2-6_5
```

With huggingface hub (credit to TheBloke for instructions):

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

To download a specific branch, use the `--revision` parameter. For example, to download the 6.5 bpw branch:

Linux:

```shell
huggingface-cli download bartowski/Codestral-22B-v0.1-exl2 --revision 6_5 --local-dir Codestral-22B-v0.1-exl2-6_5
```

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

```shell
huggingface-cli download bartowski/Codestral-22B-v0.1-exl2 --revision 6_5 --local-dir Codestral-22B-v0.1-exl2-6.5
```

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