LLM EXPLORER 62,404 MODELS INDEXED

Qwen3.5 0.8B Abliterated by xdchinza

By xdchinza · 23 downloads
HF Repo ↗ Copy URL

Qwen3.5 0.8B Abliterated is an open-source language model by xdchinza. Features: 0.8b LLM, VRAM: 1.8GB, License: apache-2.0, LLM Explorer Score: 0.28.

  Abliterated Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3.5-0.8b   Conversational   Directional-ablation   Endpoints compatible   Image-text-to-text   Mechanistic-interpretability   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow   Uncensored
Model Card on HF 🤗: https://huggingface.co/xdchinza/Qwen3.5-0.8B-abliterated 

Qwen3.5 0.8B Abliterated Parameters and Internals

LLM NameQwen3.5 0.8B Abliterated
Repository 🤗https://huggingface.co/xdchinza/Qwen3.5-0.8B-abliterated 
Base Model(s)  Qwen/Qwen3.5-0.8B   Qwen/Qwen3.5-0.8B
Model Size0.8b
Required VRAM1.8 GB
Updated2026-09-28
Maintainerxdchinza
Model Typeqwen3_5
Model Files  1.8 GB: 1-of-1
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.5 0.8B Abliterated

Best Alternatives
Context / RAM
Downloads
Likes
OvisOCR20K / 1.7 GB197760473
Qwen3.5 0.8B0K / 1.8 GB2839884655
Intern Decision 0.8B0K / 0.2 GB24216
Tev1 0.8B Experimental0K / 1.8 GB6449
Qwen3.5 0.8B Base0K / 1.8 GB82805492
PlayJev 0.8B0K / 2.2 GB3532
...iptagent Qwen35 0.8B V2 Merged0K / 3.4 GB3673
Qwen3.5 0.8B0K / 1.8 GB4766319
ORP 0.8B0K / 1.7 GB5091
Qwen3.5 0.8B Manumit V20K / 1.7 GB5930
Note: green Score (e.g. "73.2") means that the model is better than xdchinza/Qwen3.5-0.8B-abliterated.