Meta Llama 3.1 405B AWQ by RiversHaveWings

 ยป  All LLMs  ยป  RiversHaveWings  ยป  Meta Llama 3.1 405B AWQ   URL Share it on

  Arxiv:2204.05149   4-bit   Autotrain compatible   Awq   De   En   Endpoints compatible   Es   Facebook   Fr   Hi   It   Llama   Llama-3   Meta   Pt   Pytorch   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Th

Meta Llama 3.1 405B AWQ 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 AWQ (RiversHaveWings/Meta-Llama-3.1-405B-AWQ)
๐ŸŒŸ Advertise your project ๐Ÿš€

Meta Llama 3.1 405B AWQ Parameters and Internals

LLM NameMeta Llama 3.1 405B AWQ
Repository ๐Ÿค—https://huggingface.co/RiversHaveWings/Meta-Llama-3.1-405B-AWQ 
Model Size405b
Required VRAM220.4 GB
Updated2025-09-07
MaintainerRiversHaveWings
Model Typellama
Model Files  5.0 GB: 1-of-47   4.6 GB: 2-of-47   4.9 GB: 3-of-47   5.0 GB: 4-of-47   4.9 GB: 5-of-47   4.6 GB: 6-of-47   4.6 GB: 7-of-47   4.6 GB: 8-of-47   4.9 GB: 9-of-47   5.0 GB: 10-of-47   4.9 GB: 11-of-47   4.6 GB: 12-of-47   4.6 GB: 13-of-47   4.6 GB: 14-of-47   4.9 GB: 15-of-47   5.0 GB: 16-of-47   4.9 GB: 17-of-47   4.6 GB: 18-of-47   4.6 GB: 19-of-47   4.6 GB: 20-of-47   4.9 GB: 21-of-47   5.0 GB: 22-of-47   4.9 GB: 23-of-47   4.6 GB: 24-of-47   4.6 GB: 25-of-47   4.6 GB: 26-of-47   4.9 GB: 27-of-47   5.0 GB: 28-of-47   4.9 GB: 29-of-47   4.6 GB: 30-of-47   4.6 GB: 31-of-47   4.6 GB: 32-of-47   4.9 GB: 33-of-47   5.0 GB: 34-of-47   4.9 GB: 35-of-47   4.6 GB: 36-of-47   4.6 GB: 37-of-47   4.6 GB: 38-of-47   4.9 GB: 39-of-47   5.0 GB: 40-of-47   4.9 GB: 41-of-47   4.6 GB: 42-of-47   4.6 GB: 43-of-47   4.6 GB: 44-of-47   4.9 GB: 45-of-47   1.5 GB: 46-of-47   4.2 GB: 47-of-47
Supported Languagesen de fr it pt hi es th
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensemeta
Context Length131072
Model Max Length131072
Transformers Version4.43.1
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Meta Llama 3.1 405B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Meta Llama 3.1 405B Bnb 4bit128K / 214.3 GB117017
Meta Llama 3.1 405B 4bit128K / 231.9 GB12025
...ama 3.1 405B Instruct Bnb 4bit128K / 214.3 GB2746
Meta Llama 3.1 405B 2bit128K / 128 GB152
Hermes 4 405B FP8128K / 213.8 GB234716
AGI 405B128K / 191.2 GB4913
Hermes 4 405B128K / 191.2 GB40354
Hermes 4 405B GGUF128K /  GB21462
Meta Llama 3.1 405B128K / 186 GB521433808
Cogito V2 Preview Llama 405B128K / 189.7 GB129210
Note: green Score (e.g. "73.2") means that the model is better than RiversHaveWings/Meta-Llama-3.1-405B-AWQ.

Rank the Meta Llama 3.1 405B AWQ 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? 51187 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124