LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Notux 8x7b V1.3.5bpw H6 EXL2 by LoneStriker

 »  All LLMs  »  LoneStriker  »  Notux 8x7b V1.3.5bpw H6 EXL2   URL Share it on

  6   
  Autotrain compatible Base model:finetune:mistralai/... Base model:mistralai/mixtral-8...   Conversational Dataset:argilla/ultrafeedback-...   De   Dpo   En   Endpoints compatible   Es   Exl2   Fr   Instruct   It   Mixtral   Moe   Preference   Quantized   Region:us   Rlaif   Safetensors   Sharded   Tensorflow   Ultrafeedback
Model Card on HF 🤗: https://huggingface.co/LoneStriker/notux-8x7b-v1-3.5bpw-h6-exl2 

Notux 8x7b V1.3.5bpw H6 EXL2 Benchmarks

LLME Score: 0.12761
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Notux 8x7b V1.3.5bpw H6 EXL2 (LoneStriker/notux-8x7b-v1-3.5bpw-h6-exl2)
🌟 Advertise your project 🚀

Notux 8x7b V1.3.5bpw H6 EXL2 Parameters and Internals

Model Type 
Pretrained generative Sparse Mixture of Experts
Supported Languages 
English (Full proficiency), Spanish (Full proficiency), Italian (Full proficiency), German (Full proficiency), French (Full proficiency)
Training Details 
Data Sources:
argilla/ultrafeedback-binarized-preferences-cleaned
Methodology:
Direct Preference Optimization (DPO) and experimental preference tuning methods like distilled DPO (dDPO)
Training Time:
1 epoch (~10hr)
Hardware Used:
8 x H100 80GB hosted in runpod.io
LLM NameNotux 8x7b V1.3.5bpw H6 EXL2
Repository 🤗https://huggingface.co/LoneStriker/notux-8x7b-v1-3.5bpw-h6-exl2 
Base Model(s)  mistralai/Mixtral-8x7B-Instruct-v0.1   mistralai/Mixtral-8x7B-Instruct-v0.1
Required VRAM20.7 GB
Updated2025-09-23
MaintainerLoneStriker
Model Typemixtral
Instruction-BasedYes
Model Files  8.6 GB: 1-of-3   8.6 GB: 2-of-3   3.5 GB: 3-of-3
Supported Languagesen de es fr it
Quantization Typeexl2
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Notux 8x7b V1.3.5bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...M 2 8x22B Beige 2.4bpw H6 EXL264K / 42.7 GB60
...M 2 8x22B Beige 3.0bpw H6 EXL264K / 53.2 GB60
...M 2 8x22B Beige 5.0bpw H6 EXL264K / 88.5 GB60
...M 2 8x22B Beige 4.0bpw H6 EXL264K / 70.8 GB50
...B Instruct V0.1 8.0bpw H8 EXL264K / 120.2 GB101
...8x22b Instruct Oh EXL2 2.25bpw64K / 40.1 GB51
...eryTour V2 8x7B 4.5bpw H6 EXL232K / 26.5 GB72
...it MoE 2bitgs8 Metaoffload HQQ32K / 24.1 GB1519
... 4bit MoE 3bit Metaoffload HQQ32K / 22.4 GB1113
...hin 2.7 Mixtral 8x7b 8bpw EXL232K / 46.8 GB72
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/notux-8x7b-v1-3.5bpw-h6-exl2.

Rank the Notux 8x7b V1.3.5bpw H6 EXL2 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? 51544 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.
Release v20241124
  Support LLM Explorer