What are the hardware requirements for Liujgoj Cantonese Gemma4 12B CPT Unified?

Liujgoj Cantonese Gemma4 12B CPT Unified requires approximately 24.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Liujgoj Cantonese Gemma4 12B CPT Unified and how large is it?

Liujgoj Cantonese Gemma4 12B CPT Unified is developed by Yvthyvq, a model with 12b 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 Liujgoj Cantonese Gemma4 12B CPT Unified?

Liujgoj Cantonese Gemma4 12B CPT Unified is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Liujgoj Cantonese Gemma4 12B CPT Unified by Yvthyvq — VRAM 24.5GB

Name: Liujgoj Cantonese Gemma4 12B CPT Unified
Author: Yvthyvq

Liujgoj Cantonese Gemma4 12B CPT Unified is an open-source language model by Yvthyvq. Features: 12b LLM, VRAM: 24.5GB, License: apache-2.0, LLM Explorer Score: 0.26.

Cantonese Cpt Gemma4 Liujgoj Region:us Safetensors Yue Zh

Model Card on HF 🤗: https://huggingface.co/Yvthyvq/Liujgoj-Cantonese-Gemma4-12b-CPT-Unified

Liujgoj Cantonese Gemma4 12B CPT Unified Parameters and Internals

LLM Name	Liujgoj Cantonese Gemma4 12B CPT Unified
Repository 🤗	https://huggingface.co/Yvthyvq/Liujgoj-Cantonese-Gemma4-12b-CPT-Unified
Model Size	12b
Required VRAM	24.5 GB
Updated	2026-07-27
Maintainer	Yvthyvq
Model Type	gemma4
Model Files	24.5 GB
Supported Languages	zh
Model Architecture	Gemma4ForConditionalGeneration
License	apache-2.0
Transformers Version	5.14.1
Tokenizer Class	GemmaTokenizerFast
Padding Token	<pad>

Rank the Liujgoj Cantonese Gemma4 12B CPT Unified 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 Liujgoj Cantonese Gemma4 12B CPT Unified

Best Alternatives	Context / RAM	Downloads	Likes
...erGemma 4 12B Abliterated Nvf4	0K / 6.7 GB	782	3

Note: green Score (e.g. "73.2") means that the model is better than Yvthyvq/Liujgoj-Cantonese-Gemma4-12b-CPT-Unified.