What are the hardware requirements for Notux 8x7b V1 AWQ?

Notux 8x7b V1 AWQ requires approximately 24.7 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 Notux 8x7b V1 AWQ and how large is it?

Notux 8x7b V1 AWQ is developed by TheBloke, a model with 46.7b 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 Notux 8x7b V1 AWQ?

Notux 8x7b V1 AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Notux 8x7b V1 AWQ by TheBloke — VRAM 24.7GB, 32K context

Name: Notux 8x7b V1 AWQ
Author: TheBloke

Notux 8x7b V1 AWQ is an open-source language model by TheBloke. Features: 46.7b LLM, VRAM: 24.7GB, Context: 32K, License: apache-2.0, MoE, Quantized, LLM Explorer Score: 0.1.

4-bit Awq Base model:argilla/notux-8x7b-... Base model:quantized:argilla/n... Conversational Dataset:argilla/ultrafeedback-... De Dpo En Es Fr It Mixtral Moe Preference Quantized Region:us Rlaif Safetensors Sharded Tensorflow Ultrafeedback

Model Card on HF 🤗: https://huggingface.co/TheBloke/notux-8x7b-v1-AWQ

Notux 8x7b V1 AWQ Parameters and Internals

Model Type

generative, Sparse Mixture of Experts

Use Cases

Areas:

research, commercial applications

Additional Notes

AWQ (low-bit weight quantization) model files available.

Supported Languages

en (high), de (high), es (high), fr (high), it (high)

Training Details

Data Sources:

argilla/ultrafeedback-binarized-preferences-cleaned

Methodology:

Preference-tuning using DPO and MoE fine-tuning

Training Time:

1 epoch (~10hr)

Hardware Used:

8 x H100 80GB

Model Architecture:

Derived from Mixtral-8x7B-Instruct-v0.1

Input Output

Input Format:

{prompt}

Output Format:

text

LLM Name	Notux 8x7b V1 AWQ
Repository 🤗	https://huggingface.co/TheBloke/notux-8x7b-v1-AWQ
Model Name	Notux 8X7B v1
Model Creator	Argilla
Base Model(s)	Notux 8x7b V1 argilla/notux-8x7b-v1
Model Size	46.7b
Required VRAM	24.7 GB
Updated	2026-08-02
Maintainer	TheBloke
Model Type	mixtral
Model Files	10.0 GB: 1-of-3 10.0 GB: 2-of-3 4.7 GB: 3-of-3
Supported Languages	en de es fr it
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	MixtralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.37.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	float16

Rank the Notux 8x7b V1 AWQ 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 Notux 8x7b V1 AWQ

Best Alternatives	Context / RAM	Downloads	Likes
...kaLM Mixtral 8x7B V0.2 DPO AWQ	32K / 24.7 GB	6	0
Mixtral 8x7B Instruct V0.1 AWQ	32K / 24.7 GB	5	0
Karakuri Lm 8x7b Chat V0.1 AWQ	32K / 24.7 GB	7	0
Dolphin 2.7 Mixtral 8x7b AWQ	32K / 24.7 GB	2550	23
Mixtral Instruct AWQ	32K / 24.7 GB	2333	43
Functionary Medium V2.4 AWQ	32K / 24.7 GB	5	3
Mixtral 8x7B Instruct V0.1 AWQ	32K / 24.7 GB	1045	59
Mixtral 8x7B Instruct V0.1 AWQ	32K / 24.7 GB	1248	16
H2ogpt Mixtral 8x7b 32K AWQ	32K / 24.7 GB	6	0
Synatra Mixtral 8x7B AWQ	32K / 24.7 GB	8	3

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/notux-8x7b-v1-AWQ.