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

Nanbeige4.1 3B Heretic Mxfp4 by mlx-community

 »  All LLMs  »  mlx-community  »  Nanbeige4.1 3B Heretic Mxfp4   URL Share it on

  29   

Nanbeige4.1 3B Heretic Mxfp4 is an open-source language model by mlx-community. Features: 3b LLM, VRAM: 7.9GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.24.

  Abliterated Base model:finetune:heretic-or... Base model:heretic-org/nanbeig...   Conversational   Decensored   En   Heretic   Llama   Mlx   Nanbeige   Region:us   Safetensors   Sharded   Tensorflow   Uncensored   Zh
Model Card on HF 🤗: https://huggingface.co/mlx-community/Nanbeige4.1-3B-heretic-mxfp4 

Nanbeige4.1 3B Heretic Mxfp4 Benchmarks

LLME Score: 0.24011
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Nanbeige4.1 3B Heretic Mxfp4 (mlx-community/Nanbeige4.1-3B-heretic-mxfp4)
🌟 Advertise your project 🚀

Nanbeige4.1 3B Heretic Mxfp4 Parameters and Internals

LLM NameNanbeige4.1 3B Heretic Mxfp4
Repository 🤗https://huggingface.co/mlx-community/Nanbeige4.1-3B-heretic-mxfp4 
Base Model(s)  heretic-org/Nanbeige4.1-3B-heretic   heretic-org/Nanbeige4.1-3B-heretic
Model Size3b
Required VRAM7.9 GB
Updated2026-05-20
Maintainermlx-community
Model Typellama
Model Files  5.4 GB: 1-of-2   2.5 GB: 2-of-2
Supported Languagesen zh
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.57.6
Tokenizer ClassTokenizersBackend
Padding Token<unk>
Vocabulary Size166144

Best Alternatives to Nanbeige4.1 3B Heretic Mxfp4

Best Alternatives
Context / RAM
Downloads
Likes
Nanbeige4.1 3B256K / 7.9 GB2332581106
Nanbeige4.1 3B Heretic256K / 7.9 GB39350
Nanbeige4.1 3B Bf16256K / 7.9 GB713
Nanbeige4.1 3B Heretic256K / 7.9 GB271
Nanbeige4.1 3B Heretic256K / 7.9 GB60
ISA 03 Mini 3B Hybrid Preview256K / 6.5 GB8514
Llama 3.2 3B Instruct128K / 6.5 GB16749181724
Llama 3.2 3B128K / 6.5 GB1016667755
Llama 3.2 3B Instruct128K / 6.5 GB16789
Llama Email Fraud Detector128K / 6.4 GB2060
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Nanbeige4.1-3B-heretic-mxfp4.

Rank the Nanbeige4.1 3B Heretic Mxfp4 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? 53834 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