LLM EXPLORER 56,604 MODELS INDEXED

Qwen3.5 0.8B Heretic by Dingdust

By Dingdust · 17 downloads
HF Repo ↗ Copy URL

Qwen3.5 0.8B Heretic is an open-source language model by Dingdust. Features: 0.8b LLM, VRAM: 1.7GB, License: apache-2.0.

  Abliterated Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-0.8b-b...   Conversational   Decensored   Endpoints compatible   Heretic   Image-text-to-text   Qwen3 5   Region:us   Safetensors   Uncensored
Model Card on HF 🤗: https://huggingface.co/Dingdust/Qwen3.5-0.8B-heretic 

Qwen3.5 0.8B Heretic Parameters and Internals

LLM NameQwen3.5 0.8B Heretic
Repository 🤗https://huggingface.co/Dingdust/Qwen3.5-0.8B-heretic 
Base Model(s)  Qwen/Qwen3.5-0.8B-Base   Qwen/Qwen3.5-0.8B-Base
Model Size0.8b
Required VRAM1.7 GB
Updated2026-08-09
MaintainerDingdust
Model Typeqwen3_5
Model Files  1.7 GB
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.14.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.5 0.8B Heretic

Best Alternatives
Context / RAM
Downloads
Likes
OvisOCR20K / 1.7 GB96957375
SingGuard NSFA 0.8B0K / 2.2 GB9535
...e 4.6 Opus Reasoning Distilled0K / 1.8 GB81710
GRM 2.5 Air0K / 1.8 GB278
Qwen3.5 0.8B Manumit V10K / 1.7 GB1290
Qwen3.5 0.8B Legal Id Sft0K / 1.8 GB340
Qwen3.5 0.8B0K / 1.8 GB2839884655
Qwen3.5 0.8B Base0K / 1.8 GB82805492
Qwen3.5 0.8B MLX 4bit0K / 0.6 GB51135
Qwen3.5 0.8B 8bit0K / 1 GB47922
Note: green Score (e.g. "73.2") means that the model is better than Dingdust/Qwen3.5-0.8B-heretic.