What are the hardware requirements for AgentWorld 35B A3B Heretic?

AgentWorld 35B A3B Heretic requires approximately 70.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed AgentWorld 35B A3B Heretic and how large is it?

AgentWorld 35B A3B Heretic is developed by auttasak88, 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 AgentWorld 35B A3B Heretic?

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

AgentWorld 35B A3B Heretic by auttasak88 — VRAM 70.4GB

Name: AgentWorld 35B A3B Heretic
Author: auttasak88

AgentWorld 35B A3B Heretic is an open-source language model by auttasak88. Features: 35b LLM, VRAM: 70.4GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.24.

Abliterated Agent Agent-environment Base model:finetune:qwen/qwen-... Base model:qwen/qwen-agentworl... Conversational En Endpoints compatible Gguf Heretic Image-text-to-text Moe Q4 Quantized Qwen Qwen3 5 moe Region:us Safetensors Sharded Tensorflow Th World-model

Model Card on HF 🤗: https://huggingface.co/auttasak88/AgentWorld-35B-A3B-Heretic

AgentWorld 35B A3B Heretic Parameters and Internals

LLM Name	AgentWorld 35B A3B Heretic
Repository 🤗	https://huggingface.co/auttasak88/AgentWorld-35B-A3B-Heretic
Base Model(s)	Qwen AgentWorld 35B A3B Qwen/Qwen-AgentWorld-35B-A3B
Model Size	35b
Required VRAM	70.4 GB
Updated	2026-08-12
Maintainer	auttasak88
Model Type	qwen3_5_moe
Model Files	19.7 GB 21.2 GB 24.7 GB 36.9 GB 4.3 GB: 1-of-16 4.5 GB: 2-of-16 5.0 GB: 3-of-16 4.0 GB: 4-of-16 4.5 GB: 5-of-16 5.0 GB: 6-of-16 4.0 GB: 7-of-16 4.5 GB: 8-of-16 5.0 GB: 9-of-16 4.0 GB: 10-of-16 4.5 GB: 11-of-16 5.0 GB: 12-of-16 4.0 GB: 13-of-16 4.5 GB: 14-of-16 5.0 GB: 15-of-16 2.6 GB: 16-of-16
Supported Languages	en th
GGUF Quantization	Yes
Quantization Type	q4\|gguf\|q4_k\|q5_k
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Model Max Length	131072
Transformers Version	5.6.2
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the AgentWorld 35B A3B 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 AgentWorld 35B A3B Heretic

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.5 35B A3B GGUF	0K / 0.9 GB	135718	862
BigBang Aquila 35B Merged	0K / 70.3 GB	81	0
...B A3B Occamy 1.0 BF16 GGUF MTP	0K / 69.7 GB	2222	0
...35B A3B NSC ACE SABER GGUF MTP	0K / 0.9 GB	20997	20
...ERATUS Hermes MTP Vision Llama	0K / 0.9 GB	453	1
...RATUS Hermes MTP Vision Ollama	0K / 0.9 GB	110	2
Darwin 35B A3B Opus Q8 GGUF	0K / 10.7 GB	289	25
Qwen3.6 35B A3B MLX 4bit	0K / 20.5 GB	513193	6
Qwen3.6 35B A3B MLX 6bit	0K / 28.9 GB	478592	2
Qwen3.6 35B A3B MLX 8bit	0K / 37.8 GB	473537	1

Note: green Score (e.g. "73.2") means that the model is better than auttasak88/AgentWorld-35B-A3B-Heretic.