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

Mixtral 8x7B V0.1 GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Mixtral 8x7B V0.1 GPTQ   URL Share it on

  1359   
  4-bit   Autotrain compatible Base model:mistralai/mixtral-8... Base model:quantized:mistralai...   De   En   Es   Fr   Gptq   It   Mixtral   Moe   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GPTQ 

Mixtral 8x7B V0.1 GPTQ Benchmarks

ARC: 65.19 vs 96.7 (so35)-32.6%
HellaSwag: 84.72 vs 95.3 (gpt4)-11.1%
MMLU: 69.43 vs 88.3 (so35)-21.4%
TruthfulQA: 45.43 vs 59 (gpt4)-23%
WinoGrande: 81.14 vs 87.5 (gpt4)-7.3%
GSM8K: 48.29 vs 96.4 (so35)-49.9%
LLME Score: 0.17876
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

Mixtral 8x7B V0.1 GPTQ Parameters and Internals

Model Type 
mixtral
Use Cases 
Areas:
research, commercial applications
Limitations:
No moderation mechanisms as it's a pre-trained base model
Supported Languages 
fr (fluent), it (fluent), de (fluent), es (fluent), en (fluent)
Training Details 
Data Sources:
VMware Open Instruct for quantization
Context Length:
4096
Model Architecture:
Sparse Mixture of Experts
Input Output 
Input Format:
{prompt}
Accepted Modalities:
text
Output Format:
text
LLM NameMixtral 8x7B V0.1 GPTQ
Repository 🤗https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GPTQ 
Model NameMixtral 8X7B v0.1
Model CreatorMistral AI_
Base Model(s)  mistralai/Mixtral-8x7B-v0.1   mistralai/Mixtral-8x7B-v0.1
Model Size6.1b
Required VRAM23.8 GB
Updated2025-06-09
MaintainerTheBloke
Model Typemixtral
Model Files  23.8 GB
Supported Languagesfr it de es en
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16
Mixtral 8x7B V0.1 GPTQ (TheBloke/Mixtral-8x7B-v0.1-GPTQ)

Best Alternatives to Mixtral 8x7B V0.1 GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...ixtral 8x7B Instruct V0.1 GPTQ32K / 23.8 GB9087137
...Hermes 2 Mixtral 8x7B DPO GPTQ32K / 23.8 GB63426
...tLM Mixtral 8x7B Instruct GPTQ32K / 23.8 GB5373
Dolphin 2.5 Mixtral 8x7b GPTQ32K / 23.8 GB76112
...Hermes 2 Mixtral 8x7B SFT GPTQ32K / 23.8 GB3811
Bagel DPO 8x7b V0.2 GPTQ32K / 23.8 GB192
Open Gpt4 8x7B V0.2 GPTQ32K / 23.8 GB136
Sensualize Mixtral GPTQ32K / 23.8 GB325
...xtral Instruct 8x7b Zloss GPTQ32K / 23.8 GB242
Dolphin 2.7 Mixtral 8x7b GPTQ32K / 23.8 GB5019
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Mixtral-8x7B-v0.1-GPTQ.

Rank the Mixtral 8x7B V0.1 GPTQ 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? 48046 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