What are the hardware requirements for AQUA 7B?

AQUA 7B requires approximately 14.5 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed AQUA 7B and how large is it?

AQUA 7B is developed by KurmaAI, a model with 7b 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 AQUA 7B?

AQUA 7B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

AQUA 7B by KurmaAI — VRAM 14.5GB, 32K context

Name: AQUA 7B
Author: KurmaAI

AQUA 7B is an open-source language model by KurmaAI. Features: 7b LLM, VRAM: 14.5GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.2.

Arxiv:2507.20520 Base model:finetune:mistralai/... Base model:mistralai/mistral-7... Conversational Dataset:kurmaai/aqua-test-data... En Endpoints compatible Instruct Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/KurmaAI/AQUA-7B

AQUA 7B Parameters and Internals

LLM Name	AQUA 7B
Repository 🤗	https://huggingface.co/KurmaAI/AQUA-7B
Base Model(s)	mistralai/Mistral-7B-Instruct-v0.3 mistralai/Mistral-7B-Instruct-v0.3
Model Size	7b
Required VRAM	14.5 GB
Updated	2026-07-22
Maintainer	KurmaAI
Model Type	mistral
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-3 5.0 GB: 2-of-3 4.5 GB: 3-of-3
Supported Languages	en
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.52.4
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32768
Torch Data Type	bfloat16

Rank the AQUA 7B 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 AQUA 7B

Best Alternatives	Context / RAM	Downloads	Likes
...Nemo Instruct 2407 Abliterated	1000K / 24.5 GB	220	20
SpydazWeb AI HumanAI RP	512K / 14.4 GB	16	1
SpydazWeb AI HumanAI 002	512K / 14.4 GB	18	1
...daz Web AI ChatML 512K Project	512K / 14.5 GB	12	0
... Summarize 64K QLoRANET Merged	128K / 4.1 GB	11	0
...1 Summarize 64K LoRANET Merged	128K / 14.4 GB	13	0
Mistral 7B Instruct V0.2	32K / 14.4 GB	1115337	3184
Mistral 7B Instruct V0.1	32K / 14.4 GB	253629	1846
Mistral 7B Instruct V0.2	32K / 14.4 GB	1338	0
Copywriting Llm	32K / 4.1 GB	122	1

Note: green Score (e.g. "73.2") means that the model is better than KurmaAI/AQUA-7B.