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

Llama 3.3 70B Instruct EXL2 4.5bpw by Dracones

 »  All LLMs  »  Dracones  »  Llama 3.3 70B Instruct EXL2 4.5bpw   URL Share it on

  6   

Llama 3.3 70B Instruct EXL2 4.5bpw is an open-source language model by Dracones. Features: 70b LLM, VRAM: 41.4GB, Context: 128K, License: llama3.3, Quantized, Instruction-Based, LLM Explorer Score: 0.17.

Base model:meta-llama/llama-3.... Base model:quantized:meta-llam...   Conversational   De   En   Endpoints compatible   Es   Exl2   Facebook   Fr   Hi   Instruct   It   Llama   Llama-3   Meta   Pt   Pytorch   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Th
Model Card on HF 🤗: https://huggingface.co/Dracones/Llama-3.3-70B-Instruct_exl2_4.5bpw 

Llama 3.3 70B Instruct EXL2 4.5bpw Benchmarks

LLME Score: 0.1692
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3.3 70B Instruct EXL2 4.5bpw (Dracones/Llama-3.3-70B-Instruct_exl2_4.5bpw)
🌟 Advertise your project 🚀

Llama 3.3 70B Instruct EXL2 4.5bpw Parameters and Internals

LLM NameLlama 3.3 70B Instruct EXL2 4.5bpw
Repository 🤗https://huggingface.co/Dracones/Llama-3.3-70B-Instruct_exl2_4.5bpw 
Base Model(s)  meta-llama/Llama-3.3-70B-Instruct   meta-llama/Llama-3.3-70B-Instruct
Model Size70b
Required VRAM41.4 GB
Updated2026-04-11
MaintainerDracones
Model Typellama
Instruction-BasedYes
Model Files  8.5 GB: 1-of-5   8.6 GB: 2-of-5   8.5 GB: 3-of-5   8.6 GB: 4-of-5   7.2 GB: 5-of-5
Supported Languagesen fr it pt hi es th de
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licensellama3.3
Context Length131072
Model Max Length131072
Transformers Version4.47.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama 3.3 70B Instruct EXL2 4.5bpw

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 8bit1024K / 75 GB445
...B Instruct Gradient 1048K 4bit1024K / 39.7 GB153
...B Instruct Gradient 1048K 2bit1024K / 21.9 GB172
...0B Instruct Gradient 262K 4bit256K / 39.7 GB183
...0B Instruct Gradient 262K 8bit256K / 75 GB132
...0B Instruct Gradient 262K 2bit256K / 21.9 GB91
... Gradient 262K 2.25bpw H6 EXL2256K / 22.2 GB80
...t Gradient 262K 4.0bpw H6 EXL2256K / 37.2 GB41
...t Gradient 262K 3.5bpw H6 EXL2256K / 32.9 GB60
...t Gradient 262K 2.4bpw H6 EXL2256K / 23.5 GB50

Rank the Llama 3.3 70B Instruct 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? 52721 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