---
license: llama2
language:
- en
pipeline_tag: conversational
tags:
- 4.0bpw
- h8
- exl2
---
Exllamav2 4.0bpw h8 quant for [BigWeave-v6-90b](https://huggingface.co/llmixer/BigWeave-v6-90b).

Calibration dataset: [llmixer/20k_random_data](https://huggingface.co/datasets/llmixer/20k_random_data)

Fits 48GB VRAM with 4k context. Slightly lower ppl than Goliath-120b 3.0bpw.