Meta Llama 3.1 405B 4bit by mlx-community

 ยป  All LLMs  ยป  mlx-community  ยป  Meta Llama 3.1 405B 4bit   URL Share it on

  4bit   Autotrain compatible   Conversational   De   En   Endpoints compatible   Es   Facebook   Fr   Hi   It   Llama   Llama-3   Meta   Mlx   Pt   Pytorch   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Th

Meta Llama 3.1 405B 4bit Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Meta Llama 3.1 405B 4bit (mlx-community/Meta-Llama-3.1-405B-4bit)

Meta Llama 3.1 405B 4bit Parameters and Internals

LLM NameMeta Llama 3.1 405B 4bit
Repository ๐Ÿค—https://huggingface.co/mlx-community/Meta-Llama-3.1-405B-4bit 
Model Size405b
Required VRAM231.9 GB
Updated2025-02-05
Maintainermlx-community
Model Typellama
Model Files  5.2 GB: 1-of-46   5.3 GB: 2-of-46   5.2 GB: 3-of-46   5.0 GB: 4-of-46   5.0 GB: 5-of-46   5.0 GB: 6-of-46   5.3 GB: 7-of-46   5.2 GB: 8-of-46   5.0 GB: 9-of-46   5.0 GB: 10-of-46   5.0 GB: 11-of-46   5.3 GB: 12-of-46   5.2 GB: 13-of-46   5.0 GB: 14-of-46   5.0 GB: 15-of-46   5.0 GB: 16-of-46   5.3 GB: 17-of-46   5.2 GB: 18-of-46   5.0 GB: 19-of-46   5.0 GB: 20-of-46   5.0 GB: 21-of-46   5.3 GB: 22-of-46   5.2 GB: 23-of-46   5.0 GB: 24-of-46   5.0 GB: 25-of-46   5.0 GB: 26-of-46   5.3 GB: 27-of-46   5.2 GB: 28-of-46   5.0 GB: 29-of-46   5.0 GB: 30-of-46   5.0 GB: 31-of-46   5.3 GB: 32-of-46   5.2 GB: 33-of-46   5.0 GB: 34-of-46   5.0 GB: 35-of-46   5.0 GB: 36-of-46   5.3 GB: 37-of-46   5.2 GB: 38-of-46   5.0 GB: 39-of-46   5.0 GB: 40-of-46   5.0 GB: 41-of-46   5.3 GB: 42-of-46   5.2 GB: 43-of-46   5.0 GB: 44-of-46   5.0 GB: 45-of-46   2.2 GB: 46-of-46
Supported Languagesen de fr it pt hi es th
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licensemeta
Context Length131072
Model Max Length131072
Transformers Version4.42.3
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Meta Llama 3.1 405B 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Meta Llama 3.1 405B Bnb 4bit128K / 214.3 GB28789116
...ama 3.1 405B Instruct Bnb 4bit128K / 214.3 GB2635
Meta Llama 3.1 405B 2bit128K / 128 GB152
Meta Llama 3.1 405B128K / 186 GB521433808
Llama 3.1 Tulu 3 405B128K / 191.2 GB46984
Llama 3.1 405B Instruct128K / 183.1 GB53203562
Meta Llama 3.1 405B Instruct128K / 186 GB55654473
Llama 3.1 405B128K / 183.1 GB12649918
Meta Llama 3.1 405B FP8128K / 197.6 GB13149994
...ta Llama 3.1 405B Instruct FP8128K / 197.6 GB55370165
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Meta-Llama-3.1-405B-4bit.

Rank the Meta Llama 3.1 405B 4bit 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  

What open-source LLMs or SLMs are you in search of? 42577 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227