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

Meta Llama 3 Instruct 120B Cat A Llama EXL2 4.5bpw by gbueno86

 »  All LLMs  »  gbueno86  »  Meta Llama 3 Instruct 120B Cat A Llama EXL2 4.5bpw   URL Share it on

  4   

Meta Llama 3 Instruct 120B Cat A Llama EXL2 4.5bpw is an open-source language model by gbueno86. Features: 120b LLM, VRAM: 70.3GB, Context: 8K, Quantized, Instruction-Based, Merged, LLM Explorer Score: 0.13.

  Merged Model   Conversational   Endpoints compatible   Exl2   Instruct   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/gbueno86/Meta-Llama-3-Instruct-120b-Cat-a-llama-exl2-4.5bpw 

Meta Llama 3 Instruct 120B Cat A Llama EXL2 4.5bpw Benchmarks

LLME Score: 0.12701
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 Instruct 120B Cat A Llama EXL2 4.5bpw (gbueno86/Meta-Llama-3-Instruct-120b-Cat-a-llama-exl2-4.5bpw)
🌟 Advertise your project 🚀

Meta Llama 3 Instruct 120B Cat A Llama EXL2 4.5bpw Parameters and Internals

Additional Notes 
This model is a result of merging two pre-trained language models using the passthrough merge method. It demonstrates unexpected intelligence and capability, as observed by the user.
Training Details 
Methodology:
Passthrough merge method, combining layers from several models using mergekit.
LLM NameMeta Llama 3 Instruct 120B Cat A Llama EXL2 4.5bpw
Repository 🤗https://huggingface.co/gbueno86/Meta-Llama-3-Instruct-120b-Cat-a-llama-exl2-4.5bpw 
Base Model(s)  ...ma 3 Instruct 120B Cat A Llama   gbueno86/Meta-Llama-3-Instruct-120b-Cat-a-llama
Merged ModelYes
Model Size120b
Required VRAM70.3 GB
Updated2026-07-06
Maintainergbueno86
Model Typellama
Instruction-BasedYes
Model Files  8.6 GB: 1-of-9   8.6 GB: 2-of-9   8.5 GB: 3-of-9   8.5 GB: 4-of-9   8.4 GB: 5-of-9   8.5 GB: 6-of-9   8.5 GB: 7-of-9   8.5 GB: 8-of-9   2.2 GB: 9-of-9
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Meta Llama 3 Instruct 120B Cat A Llama EXL2 4.5bpw

Best Alternatives
Context / RAM
Downloads
Likes
...t 120B Cat A Llama EXL2 5.5bpw8K / 85.3 GB50
...egaDolphin 120B 2.9bpw H6 EXL24K / 44.3 GB23
...gaDolphin 120B 2.65bpw H6 EXL24K / 40.5 GB32
...egaDolphin 120B 4.0bpw H6 EXL24K / 60.8 GB41
...ma 3 Instruct 120B Cat A Llama8K / 243.9 GB21
Meta Llama 3 225B Instruct8K / 443.2 GB27418
...0B Instruct Abliterated Merged8K / 243.7 GB71
MegaDolphin 120B GPTQ4K / 61.1 GB74
MegaDolphin 120B AWQ4K / 63.3 GB82
Koishi 120B Qlora Gptq4K / 59.8 GB61
Note: green Score (e.g. "73.2") means that the model is better than gbueno86/Meta-Llama-3-Instruct-120b-Cat-a-llama-exl2-4.5bpw.

Rank the Meta Llama 3 Instruct 120B Cat A Llama EXL2 4.5bpw 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? 55064 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer