What are the hardware requirements for Qwen3.5 0.8B Heretic?

Qwen3.5 0.8B Heretic requires approximately 1.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.5 0.8B Heretic and how large is it?

Qwen3.5 0.8B Heretic is developed by sh0ck0r, a model with 0.8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Qwen3.5 0.8B Heretic?

Qwen3.5 0.8B Heretic is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3.5 0.8B Heretic by sh0ck0r — VRAM 1.7GB

Name: Qwen3.5 0.8B Heretic
Author: sh0ck0r

Qwen3.5 0.8B Heretic is an open-source language model by sh0ck0r. Features: 0.8b LLM, VRAM: 1.7GB, License: apache-2.0, LLM Explorer Score: 0.23.

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/sh0ck0r/Qwen3.5-0.8B-heretic

Qwen3.5 0.8B Heretic Parameters and Internals

LLM Name	Qwen3.5 0.8B Heretic
Repository 🤗	https://huggingface.co/sh0ck0r/Qwen3.5-0.8B-heretic
Base Model(s)	Qwen/Qwen3.5-0.8B-Base Qwen/Qwen3.5-0.8B-Base
Model Size	0.8b
Required VRAM	1.7 GB
Updated	2026-10-10
Maintainer	sh0ck0r
Model Type	qwen3_5
Model Files	1.7 GB
Model Architecture	Qwen3_5ForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	5.3.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Qwen3.5 0.8B Heretic capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to Qwen3.5 0.8B Heretic

Best Alternatives	Context / RAM	Downloads	Likes
OvisOCR2	0K / 1.7 GB	238620	483
Qwen3.5 0.8B	0K / 1.8 GB	2839884	655
Qwen3.5 0.8B Base	0K / 1.8 GB	828054	92
Xiaomi OCR 0	0K / 1.8 GB	933	15
Tev1 0.8B Onnx Webgpu	0K / GB	1336	1
Intern Decision 0.8B	0K / 0.2 GB	242	16
Tev1 0.8B Experimental	0K / 1.8 GB	644	9
OneJev 0.8B	0K / 2.2 GB	1101	2
Loopl 0.8B	0K / 1.7 GB	115	1
Vedu Scribe 0.8B	0K / 0.5 GB	65	2

Note: green Score (e.g. "73.2") means that the model is better than sh0ck0r/Qwen3.5-0.8B-heretic.