What are the hardware requirements for Qwen3.5 KETI HAECHI 27B?

Qwen3.5 KETI HAECHI 27B requires approximately 54.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.5 KETI HAECHI 27B and how large is it?

Qwen3.5 KETI HAECHI 27B is developed by KETI-AIR, 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 Qwen3.5 KETI HAECHI 27B?

Qwen3.5 KETI HAECHI 27B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3.5 KETI HAECHI 27B by KETI-AIR — VRAM 54.7GB

Name: Qwen3.5 KETI HAECHI 27B
Author: KETI-AIR

Qwen3.5 KETI HAECHI 27B is an open-source language model by KETI-AIR. Features: 27b LLM, VRAM: 54.7GB, License: apache-2.0, LLM Explorer Score: 0.25.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-27b Conversational Cultural-heritage En Endpoints compatible Image-text-to-text Ko Korean Long-horizon Multimodal Ocr Qwen3.5 Qwen3 5 Region:us Safetensors Tool-use Vision Vision-language

Model Card on HF 🤗: https://huggingface.co/KETI-AIR/Qwen3.5-KETI-HAECHI-27B

Qwen3.5 KETI HAECHI 27B Parameters and Internals

LLM Name	Qwen3.5 KETI HAECHI 27B
Repository 🤗	https://huggingface.co/KETI-AIR/Qwen3.5-KETI-HAECHI-27B
Base Model(s)	Qwen/Qwen3.5-27B Qwen/Qwen3.5-27B
Model Size	27b
Required VRAM	54.7 GB
Updated	2026-09-06
Maintainer	KETI-AIR
Model Type	qwen3_5
Model Files	54.7 GB
Supported Languages	ko en
Model Architecture	Qwen3_5ForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	4.57.0.dev0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Qwen3.5 KETI HAECHI 27B 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 Qwen3.5 KETI HAECHI 27B

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	86	3
Qwen3.8 27B NPU2	256K / GB	252	4
JEV 27B VL	0K / 55.6 GB	1525286	966
Clef	0K / 54.7 GB	22043	2237
Qwen3.8 27B NVFP4 DGX SPARK V2	0K / 19.8 GB	11317	113
Qwen3.6 27B	0K / 55.4 GB	6728138	2197
Qwen3.8 27B	0K / 55.6 GB	2	8753
Qwen3.8 27B	0K / 55.6 GB	2727	21
Qwen3.8 27B MLX	0K / 16 GB	1411	18

Note: green Score (e.g. "73.2") means that the model is better than KETI-AIR/Qwen3.5-KETI-HAECHI-27B.