LLM Explorer: A Curated Large Language Model Directory and Analytics  // 

Mistral 7B Instruct V0.1 4bit Mlx by mlx-community

What open-source LLMs or SLMs are you in search of? 18857 in total.

 ยป  All LLMs  ยป  mlx-community  ยป  Mistral 7B Instruct V0.1 4bit Mlx   URL Share it on

  4-bit   4bit   Conversational   Finetuned   Instruct   License:apache-2.0   Mistral   Mlx   Quantized   Region:us

Rank the Mistral 7B Instruct V0.1 4bit Mlx Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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  
Mistral 7B Instruct V0.1 4bit Mlx (mlx-community/Mistral-7B-Instruct-v0.1-4bit-mlx)

Best Alternatives to Mistral 7B Instruct V0.1 4bit Mlx

Best Alternatives
HF Rank
Metis Chat Instruct 7B74.6632K / 14.4 GB13530
SirUkrainian70.532K / 14.4 GB2750
Mistral 7B Merge 14 V0.369.6632K / 14.5 GB25696
Sour Marcoro 12.5B69.2332K / 25 GB7650
Mistral CatMacaroni Slerp 7B69.0832K / 14.5 GB12890
Neural Una Cybertron 7B69.0532K / 14.4 GB17272
Pic 7B Mistral Full V0.268.7232K / 15 GB20939
Instruct V0.2 Seraph 7B68.4832K / 14.4 GB24591
...lphin 2.6 Mistral 7B DPO Laser67.4332K / 14.4 GB19226
StarMix 7B Slerp67.4132K / 14.5 GB21851
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Mistral-7B-Instruct-v0.1-4bit-mlx.

Mistral 7B Instruct V0.1 4bit Mlx Parameters and Internals

LLM NameMistral 7B Instruct V0.1 4bit Mlx
RepositoryOpen on ๐Ÿค— 
Model Size7b
Required VRAM4.3 GB
Model Typemistral
Model Files  4.3 GB
Quantization Type4bit
Model ArchitectureMistralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Vocabulary Size32000
Initializer Range0.02
Torch Data Typebfloat16
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024022003