What are the hardware requirements for Qwen3.5 9B Heretic V2?

Qwen3.5 9B Heretic V2 requires approximately 18.8 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.5 9B Heretic V2 and how large is it?

Qwen3.5 9B Heretic V2 is developed by trohrbaugh, a model with 9b 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 9B Heretic V2?

Qwen3.5 9B Heretic V2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3.5 9B Heretic V2 by trohrbaugh — VRAM 18.8GB

Name: Qwen3.5 9B Heretic V2
Author: trohrbaugh

Qwen3.5 9B Heretic V2 is an open-source language model by trohrbaugh. Features: 9b LLM, VRAM: 18.8GB, License: apache-2.0, LLM Explorer Score: 0.26.

Abliterated Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-9b-bas... Conversational Decensored Endpoints compatible Heretic Image-text-to-text Qwen3 5 Region:us Safetensors Sharded Tensorflow Uncensored

Model Card on HF 🤗: https://huggingface.co/trohrbaugh/Qwen3.5-9B-heretic-v2

Qwen3.5 9B Heretic V2 Parameters and Internals

LLM Name	Qwen3.5 9B Heretic V2
Repository 🤗	https://huggingface.co/trohrbaugh/Qwen3.5-9B-heretic-v2
Base Model(s)	Qwen/Qwen3.5-9B-Base Qwen/Qwen3.5-9B-Base
Model Size	9b
Required VRAM	18.8 GB
Updated	2026-08-09
Maintainer	trohrbaugh
Model Type	qwen3_5
Model Files	9.9 GB: 1-of-2 8.9 GB: 2-of-2
Model Architecture	Qwen3_5ForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	5.2.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Qwen3.5 9B Heretic V2 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

Quantized Models of the Qwen3.5 9B Heretic V2

Model	Likes	Downloads	VRAM
Crow 9B HERETIC 4.6	280	5425	18 GB

Best Alternatives to Qwen3.5 9B Heretic V2

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.8 Distilled 9B NPU2	256K / GB	485	3
Qwen3.5 9B	0K / 19.3 GB	12207758	1799
Ornith 1.0 9B	0K / 18.8 GB	1855431	539
Qwable 9B Claude Fable 5	0K / 18.8 GB	1088	115
Qwythos 9B Claude Mythos 5 1M	0K / 18.8 GB	37427	906
Qwen3.8 9B Distill	0K / 19.3 GB	5839	148
Ornith 1.5 9B	0K / 18.9 GB	1324	120
Negentropy Claude Opus 4.7 9B	0K / 18.8 GB	63	26
Qwythos 9B V2	0K / 19.3 GB	19208	156
Ornith 1.5 9B NVFP4	0K / 8.8 GB	2704	7

Note: green Score (e.g. "73.2") means that the model is better than trohrbaugh/Qwen3.5-9B-heretic-v2.