What are the hardware requirements for Aquila2 34B?

Aquila2 34B requires approximately 136.4 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Aquila2 34B and how large is it?

Aquila2 34B is developed by BAAI, a model with 34b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Aquila2 34B perform on standard benchmarks?

Aquila2 34B has the following published scores: MMLU 76.02. Compare against reference models on this page or on the LLM Explorer leaderboards.

Aquila2 34B by BAAI — VRAM 136.4GB, 8K context

Name: Aquila2 34B
Author: BAAI

Aquila2 34B is an open-source language model by BAAI. Features: 34b LLM, VRAM: 136.4GB, Context: 8K, License: other, LLM Explorer Score: 0.12, Arc: 52.7, HellaSwag: 82, MMLU: 76, GSM8K: 0.5.

Arxiv:2408.07410 Aquila Conversational Custom code Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/BAAI/Aquila2-34B

Aquila2 34B Parameters and Internals

Model Type

base language model, chat model

Additional Notes

The Aquila2 model series includes both base language models and chat models, featuring Aquila2-7B, Aquila2-34B, AquilaChat2-7B, AquilaChat2-34B, AquilaChat2-7B-16k, and AquilaChat2-34B-16k.

Release Notes

Date:

2024.6.6

Notes:

Updated the basic language model Aquila2-34B with a new tokenizer and increased maximum processing length from 2048 to 8192.

LLM Name	Aquila2 34B
Repository 🤗	https://huggingface.co/BAAI/Aquila2-34B
Model Size	34b
Required VRAM	136.4 GB
Updated	2026-08-17
Maintainer	BAAI
Model Type	aquila
Model Files	4.5 GB: 1-of-29 4.9 GB: 2-of-29 4.9 GB: 3-of-29 4.7 GB: 4-of-29 4.9 GB: 5-of-29 4.9 GB: 6-of-29 4.9 GB: 7-of-29 4.7 GB: 8-of-29 4.9 GB: 9-of-29 4.9 GB: 10-of-29 4.9 GB: 11-of-29 4.7 GB: 12-of-29 4.9 GB: 13-of-29 4.9 GB: 14-of-29 4.9 GB: 15-of-29 4.7 GB: 16-of-29 4.9 GB: 17-of-29 4.9 GB: 18-of-29 4.9 GB: 19-of-29 4.7 GB: 20-of-29 4.9 GB: 21-of-29 4.9 GB: 22-of-29 4.9 GB: 23-of-29 4.7 GB: 24-of-29 4.9 GB: 25-of-29 4.9 GB: 26-of-29 4.9 GB: 27-of-29 2.2 GB: 28-of-29 3.5 GB: 29-of-29
Model Architecture	AquilaForCausalLM
License	other
Context Length	8192
Model Max Length	8192
Transformers Version	4.42.3
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|end_of_text\|>
Vocabulary Size	143973
Torch Data Type	float32

Rank the Aquila2 34B 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 34B

Best Alternatives	Context / RAM	Downloads	Likes
AquilaChat2 34B 16K	16K / 67.2 GB	175	26
AquilaChat2 34B	4K / 67.2 GB	138	47
H2ogpt 16K Aquilachat2 34B	4K / 67.2 GB	9	4
AquilaChat2 34B GPTQ	4K / 18.7 GB	16	2
AquilaChat2 34B 16K GPTQ	4K / 18.7 GB	7	5
AquilaChat2 34B 16K AWQ	4K / 19.3 GB	10	3
AquilaChat2 34B AWQ	4K / 19.3 GB	6	1