What are the hardware requirements for Heretical Qwen3.5 4B?

Heretical Qwen3.5 4B requires approximately 9.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Heretical Qwen3.5 4B and how large is it?

Heretical Qwen3.5 4B is developed by Kewk, a model with 4b 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 Heretical Qwen3.5 4B?

Heretical Qwen3.5 4B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Heretical Qwen3.5 4B by Kewk — VRAM 9.1GB

Name: Heretical Qwen3.5 4B
Author: Kewk

Heretical Qwen3.5 4B is an open-source language model by Kewk. Features: 4b LLM, VRAM: 9.1GB, License: apache-2.0, LLM Explorer Score: 0.23.

Abliterated Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-4b-bas... Conversational Decensored Endpoints compatible Heretic Image-text-to-text Qwen3 5 Region:us Safetensors Uncensored

Model Card on HF 🤗: https://huggingface.co/Kewk/Heretical-Qwen3.5-4B

Heretical Qwen3.5 4B Parameters and Internals

LLM Name	Heretical Qwen3.5 4B
Repository 🤗	https://huggingface.co/Kewk/Heretical-Qwen3.5-4B
Base Model(s)	Qwen/Qwen3.5-4B-Base Qwen/Qwen3.5-4B-Base
Model Size	4b
Required VRAM	9.1 GB
Updated	2026-08-26
Maintainer	Kewk
Model Type	qwen3_5
Model Files	9.1 GB
Model Architecture	Qwen3_5ForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	5.2.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Heretical Qwen3.5 4B 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 Heretical Qwen3.5 4B

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.5 4B	0K / 9.3 GB	6575502	801
NuExtract3	0K / 0.2 GB	441570	324
Agents A1 4B	0K / 9.1 GB	177578	72
Qwen3.8 4B Distill	0K / 9.3 GB	1878	26
Fara1.5 4B	0K / 9.1 GB	4934	39
Qwen3.5 4B Base	0K / 9.3 GB	227814	79
AREX Turbo	0K / 9.1 GB	1242	44
Qwen3.5 4B	0K / 9.3 GB	139961	26
DeepSeek V4 Pro Qwen3.5 4B	0K / 9.3 GB	3476	9
Mephisto 4B 0725	0K / 8.6 GB	3121	6

Note: green Score (e.g. "73.2") means that the model is better than Kewk/Heretical-Qwen3.5-4B.