What are the hardware requirements for Notus 7B V1 GPTQ?

Notus 7B V1 GPTQ requires approximately 4.2 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 Notus 7B V1 GPTQ and how large is it?

Notus 7B V1 GPTQ is developed by TheBloke, 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 Notus 7B V1 GPTQ?

Notus 7B V1 GPTQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Notus 7B V1 GPTQ by TheBloke — VRAM 4.2GB, 32K context

Name: Notus 7B V1 GPTQ
Author: TheBloke

Notus 7B V1 GPTQ is an open-source language model by TheBloke. Features: 7b LLM, VRAM: 4.2GB, Context: 32K, License: mit, Quantized, LLM Explorer Score: 0.1.

4-bit Base model:argilla/notus-7b-v1 Base model:quantized:argilla/n... Conversational Dataset:argilla/ultrafeedback-... Dpo En Gptq Mistral Model-index Preference Quantized Region:us Rlaif Safetensors Ultrafeedback

Model Card on HF 🤗: https://huggingface.co/TheBloke/notus-7B-v1-GPTQ

Notus 7B V1 GPTQ Parameters and Internals

Model Type

GPT-like, DPO fine-tuned

Additional Notes

The model's datasets contained TruthfulQA prompts which may affect benchmarking accuracy. Future releases will address this.

Supported Languages

en (Mainly English)

Training Details

Data Sources:

openbmb/UltraFeedback, argilla/ultrafeedback-binarized-preferences

Methodology:

DPO fine-tuned

Hardware Used:

VM with 8 x A100 40GB

Model Architecture:

GPT-like 7B model

Input Output

Input Format:

Prompt template: <|system|> ~~ <|user|> {prompt}~~ <|assistant|>

Accepted Modalities:

text

Output Format:

Text generation output

LLM Name	Notus 7B V1 GPTQ
Repository 🤗	https://huggingface.co/TheBloke/notus-7B-v1-GPTQ
Model Name	Notus 7B v1
Model Creator	Argilla
Base Model(s)	Notus 7B V1 argilla/notus-7b-v1
Model Size	7b
Required VRAM	4.2 GB
Updated	2026-06-07
Maintainer	TheBloke
Model Type	mistral
Model Files	4.2 GB
Supported Languages	en
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	MistralForCausalLM
License	mit
Context Length	32768
Model Max Length	32768
Transformers Version	4.35.2
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Notus 7B V1 GPTQ 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 Notus 7B V1 GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
...enHermes 2.5 Mistral 7B Marlin	32K / 4.1 GB	6	2
Zephyr 7B Beta Marlin	32K / 4.1 GB	16	0
Mistral 7B Instruct V0.3 GPTQ	32K / 4.2 GB	113881	1
...ral 7B Instruct V0.3 GPTQ 4bit	32K / 4.2 GB	2946	18
...ral 7B Instruct V0.3 GPTQ 4bit	32K / 4.2 GB	2658	25
Mistral 7B Instruct V0.2 GPTQ	32K / 4.2 GB	6743	56
...istral 7B Pruned50 GPTQ Marlin	32K / 4 GB	5	0
Cosmosage V2	32K / 4.2 GB	8	4
Mistral 7B Unsloth Gptq 8bit	32K / 7.7 GB	7	0
...phyr 7B Beta Assistant V1 Gptq	32K / 4.2 GB	2	1

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/notus-7B-v1-GPTQ.