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

L3 Stheno V3.2 12.2B Instruct by DavidAU

 »  All LLMs  »  DavidAU  »  L3 Stheno V3.2 12.2B Instruct   URL Share it on

  6   

L3 Stheno V3.2 12.2B Instruct is an open-source language model by DavidAU. Features: 8b LLM, VRAM: 42.3GB, Context: 8K, Instruction-Based, Merged, LLM Explorer Score: 0.2.

  Merged Model   Autotrain compatible   Conversational   Endpoints compatible   Instruct   Llama   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/DavidAU/L3-Stheno-v3.2-12.2B-Instruct 

L3 Stheno V3.2 12.2B Instruct Benchmarks

MMLU Pro: 26.06
GPQA: 3.36
MUSR: 10.31
BBH: 27.37
IFEval: 40.28 vs 88 (so35)-54.2%
MATH Lvl 5: 5.06
LLME Score: 0.20396
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
L3 Stheno V3.2 12.2B Instruct (DavidAU/L3-Stheno-v3.2-12.2B-Instruct)
🌟 Advertise your project 🚀

L3 Stheno V3.2 12.2B Instruct Parameters and Internals

LLM NameL3 Stheno V3.2 12.2B Instruct
Repository 🤗https://huggingface.co/DavidAU/L3-Stheno-v3.2-12.2B-Instruct 
Merged ModelYes
Model Size8b
Required VRAM42.3 GB
Updated2025-09-23
MaintainerDavidAU
Model Typellama
Instruction-BasedYes
Model Files  2.1 GB: 1-of-53   2.1 GB: 2-of-53   0.9 GB: 3-of-53   0.9 GB: 4-of-53   0.9 GB: 5-of-53   0.8 GB: 6-of-53   0.9 GB: 7-of-53   0.8 GB: 8-of-53   0.9 GB: 9-of-53   0.8 GB: 10-of-53   0.9 GB: 11-of-53   0.8 GB: 12-of-53   0.9 GB: 13-of-53   0.8 GB: 14-of-53   0.9 GB: 15-of-53   0.8 GB: 16-of-53   0.9 GB: 17-of-53   0.8 GB: 18-of-53   0.9 GB: 19-of-53   0.8 GB: 20-of-53   0.9 GB: 21-of-53   0.8 GB: 22-of-53   0.9 GB: 23-of-53   0.8 GB: 24-of-53   0.9 GB: 25-of-53   0.9 GB: 26-of-53   0.8 GB: 27-of-53   0.9 GB: 28-of-53   0.8 GB: 29-of-53   0.9 GB: 30-of-53   0.8 GB: 31-of-53   0.9 GB: 32-of-53   0.8 GB: 33-of-53   0.9 GB: 34-of-53   0.8 GB: 35-of-53   0.9 GB: 36-of-53   0.9 GB: 37-of-53   0.9 GB: 38-of-53   0.9 GB: 39-of-53   0.9 GB: 40-of-53   0.9 GB: 41-of-53   0.9 GB: 42-of-53   0.9 GB: 43-of-53   0.9 GB: 44-of-53   0.9 GB: 45-of-53   0.9 GB: 46-of-53
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.43.3
Vocabulary Size128256
Torch Data Typefloat32

Best Alternatives to L3 Stheno V3.2 12.2B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB89119
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
UltraLong Thinking4192K / 16.1 GB93
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB4017
Cthulhu 8B V1.41048K / 16.1 GB139
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB344055
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
Zero Llama 3.1 8B Beta61048K / 16.1 GB51
...dger Nu Llama 3.1 8B UltraLong1048K / 16.2 GB53
Note: green Score (e.g. "73.2") means that the model is better than DavidAU/L3-Stheno-v3.2-12.2B-Instruct.

Rank the L3 Stheno V3.2 12.2B Instruct 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