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

L3 70B Euryale V2.1 EXL2 2.3bpw by DeusImperator

 »  All LLMs  »  DeusImperator  »  L3 70B Euryale V2.1 EXL2 2.3bpw   URL Share it on

  12   
  Autotrain compatible   Conversational   En   Endpoints compatible   Exl2   Llama   Pytorch   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/DeusImperator/L3-70B-Euryale-v2.1_exl2_2.3bpw 

L3 70B Euryale V2.1 EXL2 2.3bpw Benchmarks

LLME Score: 0.17692
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
L3 70B Euryale V2.1 EXL2 2.3bpw (DeusImperator/L3-70B-Euryale-v2.1_exl2_2.3bpw)

L3 70B Euryale V2.1 EXL2 2.3bpw Parameters and Internals

Model Type 
text generation
Additional Notes 
Very creative, lots of unique swipes. Is not restrictive during roleplays. Feels like a big brained version of Stheno.
Supported Languages 
languages_supported (en), proficiency ()
Training Details 
Data Sources:
Same Dataset used as Stheno v3.2
Methodology:
LoRA Fine-Tune -> FFT is simply too expensive.
Context Length:
13500
Hardware Used:
8x H100 SXMs
Input Output 
Performance Tips:
For longer context (over 8k) it seems better to use bigger alpha_value in RoPE scaling than recommended in webui (for example at least 2.5 for 12k context).
LLM NameL3 70B Euryale V2.1 EXL2 2.3bpw
Repository 🤗https://huggingface.co/DeusImperator/L3-70B-Euryale-v2.1_exl2_2.3bpw 
Model Size70b
Required VRAM22.6 GB
Updated2025-06-01
MaintainerDeusImperator
Model Typellama
Model Files  8.6 GB: 1-of-3   8.5 GB: 2-of-3   5.5 GB: 3-of-3
Supported Languagesen
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-4.0
Context Length8192
Model Max Length8192
Transformers Version4.41.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to L3 70B Euryale V2.1 EXL2 2.3bpw

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 8bit1024K / 75 GB165
...B Instruct Gradient 1048K 4bit1024K / 39.7 GB193
...B Instruct Gradient 1048K 2bit1024K / 21.9 GB222
...0B Instruct Gradient 262K 4bit256K / 39.7 GB283
...0B Instruct Gradient 262K 2bit256K / 21.9 GB231
...0B Instruct Gradient 262K 8bit256K / 75 GB142
...t Gradient 262K 4.0bpw H6 EXL2256K / 37.2 GB221
... Gradient 262K 2.25bpw H6 EXL2256K / 22.2 GB120
...t Gradient 262K 3.5bpw H6 EXL2256K / 32.9 GB110
...t Gradient 262K 2.4bpw H6 EXL2256K / 23.5 GB100

Rank the L3 70B Euryale V2.1 EXL2 2.3bpw 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? 47770 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.
Release v20241227
  Support LLM Explorer