What are the hardware requirements for DoubleTrouble?

DoubleTrouble requires approximately 54.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed DoubleTrouble and how large is it?

DoubleTrouble is developed by OliviaRossi, a model with 27b 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 DoubleTrouble?

DoubleTrouble is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

DoubleTrouble by OliviaRossi — VRAM 54.6GB

Name: DoubleTrouble
Author: OliviaRossi

DoubleTrouble is an open-source language model by OliviaRossi. Features: 27b LLM, VRAM: 54.6GB, License: apache-2.0, LLM Explorer Score: 0.35.

Abliterated Agent Base model:davidau/qwen3.8-27b... Base model:jackrong/qwopus3.8-... Base model:merge:davidau/qwen3... Base model:merge:jackrong/qwop... Conversational En Endpoints compatible Flash Gated-deltanet Image-text-to-text Llama.cpp Merge Multimodal Normalized-geodesic-consensus Qwen Qwen3.5 Qwen3.8 Qwen3 5 Reasoning Region:us Safetensors Sharded Tensorflow Uncensored Vision Vllm Zh

Model Card on HF 🤗: https://huggingface.co/OliviaRossi/DoubleTrouble

DoubleTrouble Parameters and Internals

LLM Name	DoubleTrouble
Repository 🤗	https://huggingface.co/OliviaRossi/DoubleTrouble
Model Name	/mnt/w/Qwen3.8-27B-Brainwaves-NM-HERETIC
Model Creator	OliviaRossi
Base Model(s)	DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored Jackrong/Qwopus3.8-27B-Flash DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored Jackrong/Qwopus3.8-27B-Flash
Model Size	27b
Required VRAM	54.6 GB
Updated	2026-09-16
Maintainer	OliviaRossi
Model Type	qwen3_5
Model Files	2.5 GB: 1-of-12 4.8 GB: 2-of-12 5.0 GB: 3-of-12 4.9 GB: 4-of-12 5.0 GB: 5-of-12 4.9 GB: 6-of-12 5.0 GB: 7-of-12 4.9 GB: 8-of-12 5.0 GB: 9-of-12 4.9 GB: 10-of-12 4.9 GB: 11-of-12 2.8 GB: 12-of-12
Supported Languages	en zh
Model Architecture	Qwen3_5ForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	5.14.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the DoubleTrouble 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 DoubleTrouble

Best Alternatives	Context / RAM	Downloads	Likes
...wopus3.8 27B Flash Mlx OQ4e 1M	1024K / 16.9 GB	211	1
Agens Pilot	1024K / 54.7 GB	139	1
Qwen3.6 27B	0K / 55.4 GB	6728138	2197
Qwen3.8 27B	0K / 55.6 GB	2	8753
Qwen3.8 27B MLX	0K / 16 GB	1411	18
Qwen3.8 27B FP8	0K / 0.4 GB	123157	416
Qwen3.8 27B	0K / 55.6 GB	2727	21
Qwen3.6 27B NVFP4	0K / 22 GB	1887525	419
Qwen3.8 27B NVFP4	0K / 22 GB	19195	74
Qwen3.6 27B FP8	0K / 0.4 GB	7740472	342

Note: green Score (e.g. "73.2") means that the model is better than OliviaRossi/DoubleTrouble.