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

Daredevil 8B Abliterated by mlabonne

 »  All LLMs  »  mlabonne  »  Daredevil 8B Abliterated   URL Share it on

  7697   

Daredevil 8B Abliterated is an open-source language model by mlabonne. Features: 8b LLM, VRAM: 16.1GB, Context: 8K, License: other, Instruction-Based, HF Score: 71.8, LLM Explorer Score: 0.24, Arc: 68.6, HellaSwag: 84.4, MMLU: 69, TruthfulQA: 57.9, WinoGrande: 77.9, GSM8K: 73.2.

Base model:finetune:mlabonne/d... Base model:mlabonne/daredevil-...   Conversational   Endpoints compatible   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlabonne/Daredevil-8B-abliterated 

Daredevil 8B Abliterated Benchmarks

MMLU Pro: 30.01
GPQA: 5.37
MUSR: 9.18
BBH: 19.87
IFEval: 44.26 vs 88 (so35)-49.7%
ARC: 68.6 vs 96.7 (so35)-29.1%
HellaSwag: 84.39 vs 95.3 (gpt4)-11.4%
MMLU: 68.99 vs 88.3 (so35)-21.9%
TruthfulQA: 57.87 vs 59 (gpt4)-1.9%
WinoGrande: 77.9 vs 87.5 (gpt4)-11%
GSM8K: 73.16 vs 96.4 (so35)-24.1%
MATH Lvl 5: 9.44
LLME Score: 0.2371
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Daredevil 8B Abliterated (mlabonne/Daredevil-8B-abliterated)
🌟 Advertise your project 🚀

Daredevil 8B Abliterated Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
role-playing
Additional Notes 
Abliterated version using failspy's notebook, based on a technique described in a specific blog post.
LLM NameDaredevil 8B Abliterated
Repository 🤗https://huggingface.co/mlabonne/Daredevil-8B-abliterated 
Base Model(s)  Daredevil 8B   mlabonne/Daredevil-8B
Model Size8b
Required VRAM16.1 GB
Updated2026-04-05
Maintainermlabonne
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.41.0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Quantized Models of the Daredevil 8B Abliterated

Model
Likes
Downloads
VRAM
Daredevil 8B Abliterated GPTQ135 GB
Daredevil 8B Abliterated AWQ065 GB

Best Alternatives to Daredevil 8B Abliterated

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB89119
UltraLong Thinking4192K / 16.1 GB73
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB12017
Cthulhu 8B V1.41048K / 16.1 GB129
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB457756
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
Zero Llama 3.1 8B Beta61048K / 16.1 GB41
...dger Nu Llama 3.1 8B UltraLong1048K / 16.2 GB123
Note: green Score (e.g. "73.2") means that the model is better than mlabonne/Daredevil-8B-abliterated.

Rank the Daredevil 8B Abliterated 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? 53493 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