What are the hardware requirements for Qwen3.6 27B Della Deckard V1?

Qwen3.6 27B Della Deckard V1 requires approximately 54.8 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.6 27B Della Deckard V1 and how large is it?

Qwen3.6 27B Della Deckard V1 is developed by YFC-112358, 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 Qwen3.6 27B Della Deckard V1?

Qwen3.6 27B Della Deckard V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3.6 27B Della Deckard V1 by YFC-112358 — VRAM 54.8GB

Name: Qwen3.6 27B Della Deckard V1
Author: YFC-112358

Qwen3.6 27B Della Deckard V1 is an open-source language model by YFC-112358. Features: 27b LLM, VRAM: 54.8GB, LLM Explorer Score: 0.3.

Qwen3 5 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/YFC-112358/Qwen3.6-27B-Della-Deckard-v1

Qwen3.6 27B Della Deckard V1 Parameters and Internals

LLM Name	Qwen3.6 27B Della Deckard V1
Repository 🤗	https://huggingface.co/YFC-112358/Qwen3.6-27B-Della-Deckard-v1
Model Size	27b
Required VRAM	54.8 GB
Updated	2026-08-18
Maintainer	YFC-112358
Model Type	qwen3_5
Model Files	2.5 GB: 1-of-26 2.1 GB: 2-of-26 2.1 GB: 3-of-26 2.1 GB: 4-of-26 2.1 GB: 5-of-26 2.1 GB: 6-of-26 2.1 GB: 7-of-26 2.1 GB: 8-of-26 2.1 GB: 9-of-26 2.1 GB: 10-of-26 2.1 GB: 11-of-26 2.1 GB: 12-of-26 1.6 GB: 13-of-26 2.5 GB: 14-of-26 2.0 GB: 15-of-26 2.1 GB: 16-of-26 2.1 GB: 17-of-26 2.1 GB: 18-of-26 2.1 GB: 19-of-26 2.1 GB: 20-of-26 2.1 GB: 21-of-26 2.1 GB: 22-of-26 2.1 GB: 23-of-26 2.1 GB: 24-of-26 2.1 GB: 25-of-26 2.1 GB: 26-of-26
Model Architecture	Qwen3_5ForConditionalGeneration
Model Max Length	262144
Transformers Version	4.57.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Qwen3.6 27B Della Deckard V1 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 27B Della Deckard V1

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.8 27B FP8	0K / 0.4 GB	123157	416
Qwen3.6 27B	0K / 55.4 GB	6728138	2197
Qwen3.8 27B	0K / 55.6 GB	2	8753
Qwen3.6 27B NVFP4	0K / 22 GB	1887525	419
Huihui Qwen3.8 27B Abliterated	0K / 55.6 GB	1485	76
ThinkingCap Qwen3.6 27B	0K / 54.7 GB	35947	614
Qwen3.6 27B FP8	0K / 0.4 GB	7740472	342
...n3.8 27B MTPLX Optimized Speed	0K / 19.6 GB	6989	50
Qwen3.5 27B	0K / 55.2 GB	2536294	1028
Qwen3.5 27B	0K / 55.2 GB	8115	16

Note: green Score (e.g. "73.2") means that the model is better than YFC-112358/Qwen3.6-27B-Della-Deckard-v1.