What are the hardware requirements for Notux 8x7b V1?

Notux 8x7b V1 requires approximately 93.6 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 and how large is it?

Notux 8x7b V1 is developed by argilla, 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.

How does Notux 8x7b V1 perform on standard benchmarks?

Notux 8x7b V1 has the following published scores: MMLU 71.39. Compare against reference models on this page or on the LLM Explorer leaderboards.

Notux 8x7b V1 by argilla — VRAM 93.6GB, 32K context

Name: Notux 8x7b V1
Author: argilla

Notux 8x7b V1 is an open-source language model by argilla. Features: 46.7b LLM, VRAM: 93.6GB, Context: 32K, License: apache-2.0, MoE, Instruction-Based, LLM Explorer Score: 0.19, Arc: 70.7, HellaSwag: 87.7, MMLU: 71.4, GSM8K: 61.1.

Base model:finetune:mistralai/... Base model:mistralai/mixtral-8... Conversational Dataset:argilla/ultrafeedback-... De Dpo En Endpoints compatible Es Fr Instruct It Mixtral Moe Preference Region:us Rlaif Safetensors Sharded Tensorboard Tensorflow Ultrafeedback

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

Notux 8x7b V1 Benchmarks

ARC: 70.65 vs 96.7 (so35)^-26.9%

HellaSwag: 87.72 vs 95.3 (gpt4)^-8%

MMLU: 71.39 vs 88.3 (so35)^-19.2%

GSM8K: 61.11 vs 96.4 (so35)^-36.6%

LLME Score: 0.19279

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

🌟 Advertise your project 🚀

Notux 8x7b V1 Parameters and Internals

Model Type

Pretrained generative Sparse Mixture of Experts

Supported Languages

en (N/A), de (N/A), es (N/A), fr (N/A), it (N/A)

Training Details

Data Sources:

argilla/ultrafeedback-binarized-preferences-cleaned

Methodology:

Preference tuning using Direct Preference Optimization (DPO) and distilled DPO (dDPO).

Training Time:

~10hr

Hardware Used:

8 x H100 80GB GPUs hosted in runpod.io

LLM Name	Notux 8x7b V1
Repository 🤗	https://huggingface.co/argilla/notux-8x7b-v1
Base Model(s)	mistralai/Mixtral-8x7B-Instruct-v0.1 mistralai/Mixtral-8x7B-Instruct-v0.1
Model Size	46.7b
Required VRAM	93.6 GB
Updated	2026-05-20
Maintainer	argilla
Model Type	mixtral
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-19 5.0 GB: 2-of-19 5.0 GB: 3-of-19 4.9 GB: 4-of-19 5.0 GB: 5-of-19 5.0 GB: 6-of-19 4.9 GB: 7-of-19 5.0 GB: 8-of-19 5.0 GB: 9-of-19 4.9 GB: 10-of-19 5.0 GB: 11-of-19 5.0 GB: 12-of-19 5.0 GB: 13-of-19 4.9 GB: 14-of-19 5.0 GB: 15-of-19 5.0 GB: 16-of-19 4.9 GB: 17-of-19 5.0 GB: 18-of-19 4.2 GB: 19-of-19 0.0 GB
Supported Languages	en de es fr it
Model Architecture	MixtralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.36.0
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Quantized Models of the Notux 8x7b V1

Model	Likes	Downloads	VRAM
Notux 8x7b V1 GGUF	5	729	15 GB
Notux 8x7b V1 GGUF	0	98	17 GB
Notux 8x7b V1 GPTQ	2	44	23 GB
Notux 8x7b V1 AWQ	3	17	24 GB

Best Alternatives to Notux 8x7b V1

Best Alternatives	Context / RAM	Downloads	Likes
Mixtral 8x7B Instruct V0.1	32K / 93.6 GB	902432	4691
Mixtral 8x7B Instruct V0.1 FP8	32K / 47.1 GB	102012	0
Merge Mixtral Prometheus 8x7B	32K / 91.9 GB	83	2
...xtral 8x7B Yes Instruct LimaRP	32K / 93.5 GB	7	1
BagelMIsteryTour V2 8x7B	32K / 93.5 GB	100	17
...rkrautLM Mixtral 8x7B Instruct	32K / 93.6 GB	226	22
Mixtral 8x7B Instruct V0.1 FP8	32K / 47.1 GB	374	0
Sage Ft Mixtral 8x7b	32K / 90 GB	65	25
Dolphin 2.5 Mixtral 8x7b	32K / 93.6 GB	4125	1235
Dolphin 2.5 Mixtral 8x7b	32K / 93.6 GB	2037	1244

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

Rank the Notux 8x7b V1 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 54415 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Notux 8x7b V1 by argilla