# Exllama v2 Llama-3-8B-Instruct-ortho-v2

Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.21">turboderp's ExLlamaV2 v0.0.21</a> for quantization.

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

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

Original model by <a href="https://huggingface.co/hjhj3168">hjhj3168</a><br>
Calibration dataset: <a href="https://huggingface.co/datasets/cosmicvalor/toxic-qna">toxic-qna</a>

## Available sizes

| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (8K) | VRAM (16k) | VRAM (32k) | Description |
| ----- | ---- | ------- | ------ | ------ | ------ | ------ | ------------ |
| [8_0](https://huggingface.co/Apel-sin/llama-3-8B-ortho-v2-exl2/tree/8_0) | 8.0 | 8.0 | 10.1 GB | 10.5 GB | 11.5 GB | 13.6 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
| [6_5](https://huggingface.co/Apel-sin/llama-3-8B-ortho-v2-exl2/tree/6_5) | 6.5 | 8.0 | 8.9 GB | 9.3 GB | 10.3 GB | 12.4 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |