LLM EXPLORER 66,704 MODELS INDEXED

LFM3 1.7B ARA Abliterated by Austriani

By Austriani · 48 downloads
HF Repo ↗ Copy URL

LFM3 1.7B ARA Abliterated is an open-source language model by Austriani. Features: 1.7b LLM, VRAM: 3.5GB, Context: 256K, License: other, Instruction-Based.

  1.7b   Abliterated   Agent   Ara   Arbitrary-rank-ablation Base model:finetune:liquidai/l...   Base model:liquidai/lfm3-1.7b   Chat   Conversational   Convolutional   Creative-writing   Custom code   Decensored   Edge-deployment   En   Endpoints compatible   Heretic   Hybrid-attention   Instruct   Kld-0.0374   Lfm3   Lfm3-1.7b   Liquid   Liquid-ai   Long-context   Refusal-removed   Region:us   Roleplay   Safetensors   Uncensored
Model Card on HF 🤗: https://huggingface.co/Austriani/LFM3-1.7B-ARA-Abliterated 

LFM3 1.7B ARA Abliterated Parameters and Internals

LLM NameLFM3 1.7B ARA Abliterated
Repository 🤗https://huggingface.co/Austriani/LFM3-1.7B-ARA-Abliterated 
Base Model(s)  LiquidAI/LFM3-1.7B   LiquidAI/LFM3-1.7B
Model Size1.7b
Required VRAM3.5 GB
Updated2026-11-06
MaintainerAustriani
Model Typelfm3
Instruction-BasedYes
Model Files  3.5 GB
Supported Languagesen
Model ArchitectureLfm3ForCausalLM
Licenseother
Context Length262144
Model Max Length262144
Transformers Version5.22.1
Tokenizer ClassTokenizersBackend
Padding Token<|pad|>
Vocabulary Size128000

Best Alternatives to LFM3 1.7B ARA Abliterated

Best Alternatives
Context / RAM
Downloads
Likes
Cosmic Lightning256K / 3.5 GB1689
LFM3 1.7B Kazakh256K / 3.5 GB4760
LFM3 1.7B Claude Fable5.1256K / 1.1 GB13042
Note: green Score (e.g. "73.2") means that the model is better than Austriani/LFM3-1.7B-ARA-Abliterated.