What are the hardware requirements for Sakura 13B Galgame?

Sakura 13B Galgame requires approximately 27.8 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Sakura 13B Galgame and how large is it?

Sakura 13B Galgame is developed by sakuraumi, a model with 13b 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 Sakura 13B Galgame?

Sakura 13B Galgame is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Sakura 13B Galgame by sakuraumi — VRAM 27.8GB

Name: Sakura 13B Galgame
Author: sakuraumi

Sakura 13B Galgame is an open-source language model by sakuraumi. Features: 13b LLM, VRAM: 27.8GB, License: apache-2.0, LLM Explorer Score: 0.09.

Baichuan Custom code Endpoints compatible Ja Pytorch Region:us Sharded Zh

Model Card on HF 🤗: https://huggingface.co/sakuraumi/Sakura-13B-Galgame

Sakura 13B Galgame Parameters and Internals

Model Type

text generation, translation

Use Cases

Areas:

Research, Educational

Applications:

Translation of Galgames and light novels

Primary Use Cases:

Galgame and light novel translations

Limitations:

Not suitable for commercial use as stated in the CC BY-NC-SA 4.0 license

Considerations:

Ensure proper attribution when using translations publicly.

Additional Notes

Model supports API backend compatible with OpenAI format. Ongoing updates to improve translation quality. Issues, feedback, and improvements are actively monitored.

Supported Languages

Chinese (Advanced), Japanese (Advanced)

Training Details

Data Sources:

Qwen model series, Qwen1.5 model series

Methodology:

Finetuning

Input Output

Input Format:

Prompts formatted for text translation

Accepted Modalities:

text

Output Format:

Translated text in simplified Chinese

Performance Tips:

Ensure using the model versioning to attain consistent quality.

Release Notes

Version:

v0.9

Date:

2024-02-13

Notes:

Enhanced quality with more stable output compared to earlier beta versions and was pre-trained on larger datasets.

LLM Name	Sakura 13B Galgame
Repository 🤗	https://huggingface.co/sakuraumi/Sakura-13B-Galgame
Model Size	13b
Required VRAM	27.8 GB
Updated	2026-07-03
Maintainer	sakuraumi
Model Type	baichuan
Model Files	10.0 GB: 1-of-3 9.9 GB: 2-of-3 7.9 GB: 3-of-3
Supported Languages	zh ja
Model Architecture	BaichuanForCausalLM
License	apache-2.0
Model Max Length	4096
Transformers Version	4.33.2
Tokenizer Class	BaichuanTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	125696
Torch Data Type	bfloat16

Rank the Sakura 13B Galgame 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 Sakura 13B Galgame

Best Alternatives	Context / RAM	Downloads	Likes
Baichuan2 13B Chat	0K / 27.8 GB	10475	432
Tiny Random Baichuan2 13B	0K / 0.1 GB	720	0
Baichuan 13B Chat	0K / 26.5 GB	3749	632
ShieldLM 13B Baichuan2	0K / 27.8 GB	8	3
Baichuan2 13B Base	0K / 27.8 GB	2267	82
Blossom V3.1 Baichuan2 13B	0K / 27.8 GB	18	1
HuatuoGPT2 13B	0K / 29.1 GB	26	8
Buffer Baichuan2 13B Rag 4bits	0K / 9.9 GB	9	0
Buffer Baichuan2 13B Rag	0K / 27.8 GB	11	1
... Efficient Training Of LLMs V1	0K / 29.1 GB	11	1

Note: green Score (e.g. "73.2") means that the model is better than sakuraumi/Sakura-13B-Galgame.