What are the hardware requirements for Aquila2 70B Expr 4.0bpw H6 EXL2?

Aquila2 70B Expr 4.0bpw H6 EXL2 requires approximately 36.6 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Aquila2 70B Expr 4.0bpw H6 EXL2 and how large is it?

Aquila2 70B Expr 4.0bpw H6 EXL2 is developed by LoneStriker, a model with 70b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Aquila2 70B Expr 4.0bpw H6 EXL2?

Aquila2 70B Expr 4.0bpw H6 EXL2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Aquila2 70B Expr 4.0bpw H6 EXL2 by LoneStriker — VRAM 36.6GB, 4K context

Name: Aquila2 70B Expr 4.0bpw H6 EXL2
Author: LoneStriker

Aquila2 70B Expr 4.0bpw H6 EXL2 is an open-source language model by LoneStriker. Features: 70b LLM, VRAM: 36.6GB, Context: 4K, License: other, Quantized, LLM Explorer Score: 0.1.

Aquila Endpoints compatible Exl2 Pytorch Quantized Region:us Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/LoneStriker/Aquila2-70B-Expr-4.0bpw-h6-exl2

Aquila2 70B Expr 4.0bpw H6 EXL2 Parameters and Internals

Model Type

chat model, language model

Supported Languages

English (Unknown proficiency), Chinese (Unknown proficiency)

LLM Name	Aquila2 70B Expr 4.0bpw H6 EXL2
Repository 🤗	https://huggingface.co/LoneStriker/Aquila2-70B-Expr-4.0bpw-h6-exl2
Model Size	70b
Required VRAM	36.6 GB
Updated	2026-07-13
Maintainer	LoneStriker
Model Type	aquila
Model Files	8.5 GB: 1-of-5 8.6 GB: 2-of-5 8.5 GB: 3-of-5 8.5 GB: 4-of-5 2.5 GB: 5-of-5
Quantization Type	exl2
Model Architecture	AquilaForCausalLM
License	other
Context Length	4096
Model Max Length	4096
Transformers Version	4.31.0
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	100008
Torch Data Type	bfloat16

Rank the Aquila2 70B Expr 4.0bpw H6 EXL2 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Aquila2 70B Expr 4.0bpw H6 EXL2

Best Alternatives	Context / RAM	Downloads	Likes
AquilaChat2 70B Expr	4K / 66.5 GB	209	5
Aquila2 70B Expr	4K / 68.2 GB	175	10

Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Aquila2-70B-Expr-4.0bpw-h6-exl2.