What are the hardware requirements for Qwen3.6 35B A3B Fable 5 Distill Heretic?

Qwen3.6 35B A3B Fable 5 Distill Heretic requires approximately 70.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.6 35B A3B Fable 5 Distill Heretic and how large is it?

Qwen3.6 35B A3B Fable 5 Distill Heretic is developed by Authereon, a model with 35b 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 Qwen3.6 35B A3B Fable 5 Distill Heretic?

Qwen3.6 35B A3B Fable 5 Distill Heretic is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3.6 35B A3B Fable 5 Distill Heretic by Authereon — VRAM 70.2GB

Name: Qwen3.6 35B A3B Fable 5 Distill Heretic
Author: Authereon

Qwen3.6 35B A3B Fable 5 Distill Heretic is an open-source language model by Authereon. Features: 35b LLM, VRAM: 70.2GB, License: apache-2.0.

Arxiv:2507.07417 Arxiv:2510.09023 Base model:armand0e/qwen3.6-35... Base model:finetune:armand0e/q... Chain-of-thought Conversational Distillation Dpo En Endpoints compatible Heretic Image-text-to-text Mixture-of-experts Moe Prompt-injection-defense Qwen Qwen3.6 Qwen3 5 moe Reasoning Region:us Safetensors Sharded Tensorflow Uncensored

Model Card on HF 🤗: https://huggingface.co/Authereon/Qwen3.6-35B-A3B-Fable-5-Distill-heretic

Qwen3.6 35B A3B Fable 5 Distill Heretic Parameters and Internals

LLM Name	Qwen3.6 35B A3B Fable 5 Distill Heretic
Repository 🤗	https://huggingface.co/Authereon/Qwen3.6-35B-A3B-Fable-5-Distill-heretic
Model Name	Qwen/Qwen3.6-35B-A3B
Base Model(s)	armand0e/Qwen3.6-35B-A3B-Fable-5-Distill armand0e/Qwen3.6-35B-A3B-Fable-5-Distill
Model Size	35b
Required VRAM	70.2 GB
Updated	2026-11-06
Maintainer	Authereon
Model Type	qwen3_5_moe
Model Files	49.7 GB: 1-of-2 19.6 GB: 2-of-2 0.9 GB: 3-of-3
Supported Languages	en
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	5.14.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Qwen3.6 35B A3B Fable 5 Distill 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 Qwen3.6 35B A3B Fable 5 Distill Heretic

Best Alternatives	Context / RAM	Downloads	Likes
....5 35B A3B Sceptic V3 1M W4A16	1024K / 26.1 GB	223	0
...AgentWorld 35B A3B Abliterated	256K / 69.2 GB	962	18
Ornith 1.5 35B A3B NPU2	256K / GB	58	0
Qwen3.6 35B A3B NPU2	256K / GB	82	0
Qwen3.6 35B A3B	0K / 72.2 GB	5540855	2648
Qwen3.5 35B A3B	0K / 72.3 GB	2158511	1482
JEV 35B	0K / 72.3 GB	713162	403
Qwen3.6 35B A3B NVFP4	0K / 23.4 GB	8788684	482
Ornith 1.0 35B	0K / 70.4 GB	1458200	519
Qwen3.6 35B A3B FP8	0K / 0.8 GB	8984811	343

Note: green Score (e.g. "73.2") means that the model is better than Authereon/Qwen3.6-35B-A3B-Fable-5-Distill-heretic.