Nanbeige4.1 3B Heretic 8bit by mlx-community

 »  All LLMs  »  mlx-community  »  Nanbeige4.1 3B Heretic 8bit   URL Share it on

Nanbeige4.1 3B Heretic 8bit is an open-source language model by mlx-community. Features: 3b LLM, VRAM: 4.2GB, Context: 256K, License: apache-2.0, Quantized, LLM Explorer Score: 0.26.

  8-bit   8bit   Abliterated Base model:daizee/nanbeige4.1-... Base model:quantized:daizee/na...   Conversational   Decensored   En   Heretic   Llama   Mlx   Nanbeige   Quantized   Region:us   Safetensors   Uncensored   Zh

Nanbeige4.1 3B Heretic 8bit Benchmarks

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 8bit Parameters and Internals

LLM NameNanbeige4.1 3B Heretic 8bit
Repository 🤗https://huggingface.co/mlx-community/Nanbeige4.1-3B-heretic-8bit 
Base Model(s)  Daizee/Nanbeige4.1-3B-heretic   Daizee/Nanbeige4.1-3B-heretic
Model Size3b
Required VRAM4.2 GB
Updated2026-04-13
Maintainermlx-community
Model Typellama
Model Files  4.2 GB
Supported Languagesen zh
Quantization Type8bit
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.57.3
Tokenizer ClassTokenizersBackend
Padding Token<unk>
Vocabulary Size166144

Best Alternatives to Nanbeige4.1 3B Heretic 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Nanbeige4.1 3B 8bit256K / 4.2 GB73314
Llama3.2 3B Base Math128K / 6.5 GB4000
Llama3.2 3B Base Code128K / 6.5 GB3750
...2 3B Instruct Unsloth Bnb 4bit128K / 2.4 GB10642210
Llama32 3B En Emo 2000 Stp128K / 2.2 GB950
Llama32 3B En Emo 300 Stp128K / 2.2 GB90
Llama32 3B En Emo 1000 Stp128K / 2.2 GB60
Llama32 3B En Emo 5000 Stp128K / 2.2 GB50
...ngCore 3B Instruct R01 Reflect128K / 6.5 GB01
ReasoningCore 3B 0128K / 6.5 GB292
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Nanbeige4.1-3B-heretic-8bit.

Rank the Nanbeige4.1 3B Heretic 8bit 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? 53053 in total.

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