What are the hardware requirements for Qwen3 1.7B Magic Decensored?

Qwen3 1.7B Magic Decensored requires approximately 3.4 GB of VRAM and supports a context window of 40K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3 1.7B Magic Decensored and how large is it?

Qwen3 1.7B Magic Decensored is developed by MagicalAlchemist, a model with 1.7b 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 1.7B Magic Decensored?

Qwen3 1.7B Magic Decensored is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3 1.7B Magic Decensored by MagicalAlchemist — VRAM 3.4GB, 40K context

Name: Qwen3 1.7B Magic Decensored
Author: MagicalAlchemist

Qwen3 1.7B Magic Decensored is an open-source language model by MagicalAlchemist. Features: 1.7b LLM, VRAM: 3.4GB, Context: 40K, License: apache-2.0, LLM Explorer Score: 0.21.

Arxiv:2505.09388 Abliterated Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-1.7b-bas... Conversational Decensored Endpoints compatible Heretic Qwen3 Region:us Safetensors Uncensored

Model Card on HF 🤗: https://huggingface.co/MagicalAlchemist/Qwen3-1.7B-Magic_decensored

Qwen3 1.7B Magic Decensored Parameters and Internals

LLM Name	Qwen3 1.7B Magic Decensored
Repository 🤗	https://huggingface.co/MagicalAlchemist/Qwen3-1.7B-Magic_decensored
Base Model(s)	Qwen/Qwen3-1.7B-Base Qwen/Qwen3-1.7B-Base
Model Size	1.7b
Required VRAM	3.4 GB
Updated	2026-10-26
Maintainer	MagicalAlchemist
Model Type	qwen3
Model Files	3.4 GB
Model Architecture	Qwen3ForCausalLM
License	apache-2.0
Context Length	40960
Model Max Length	40960
Transformers Version	4.57.6
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Errors	replace

Rank the Qwen3 1.7B Magic Decensored 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 1.7B Magic Decensored

Best Alternatives	Context / RAM	Downloads	Likes
Reaper Base	128K / 3.4 GB	393	0
Lucy 128K	128K / 3.4 GB	123	112
Polaris 1.7B Preview	128K / 3.4 GB	73	8
DictaLM 3.0 1.7B Instruct	60K / 3.4 GB	2842	1
Qwen3 1.7B	40K / 4 GB	5633291	500
Boole 1.7B	40K / 0.2 GB	539	9
Stormdesks Triage	40K / 3.4 GB	309	1
Stormdesk Triage	40K / 3.4 GB	461	1
Qwen3 1.7B SPFT Ultrafeedback	40K / 3.4 GB	312	1
Qwen3 1.7B SFT Ultrafeedback	40K / 3.4 GB	299	1

Note: green Score (e.g. "73.2") means that the model is better than MagicalAlchemist/Qwen3-1.7B-Magic_decensored.