What are the hardware requirements for Japanese Novel GPT J 6B F16 Marisa?

Japanese Novel GPT J 6B F16 Marisa requires approximately 12.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Japanese Novel GPT J 6B F16 Marisa and how large is it?

Japanese Novel GPT J 6B F16 Marisa is developed by tsukemono, a model with 6b 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 Japanese Novel GPT J 6B F16 Marisa?

Japanese Novel GPT J 6B F16 Marisa is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Japanese Novel GPT J 6B F16 Marisa by tsukemono — VRAM 12.2GB

Name: Japanese Novel GPT J 6B F16 Marisa
Author: tsukemono

Japanese Novel GPT J 6B F16 Marisa is an open-source language model by tsukemono. Features: 6b LLM, VRAM: 12.2GB, Quantized, LLM Explorer Score: 0.08.

Endpoints compatible Fp16 Gptj Ja Pytorch Quantized Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/tsukemono/japanese-novel-gpt-j-6b-f16-marisa

Japanese Novel GPT J 6B F16 Marisa Parameters and Internals

Model Type

text-generation

Use Cases

Areas:

research, entertainment

Primary Use Cases:

chatting with the character Marisa Kirisame from Touhou Project

Additional Notes

This is a secondary creation from the Touhou Project.

Supported Languages

Japanese (Fluent)

Input Output

Input Format:

"ユーザー: hogehoge[SEP]魔理沙: "

Accepted Modalities:

text

LLM Name	Japanese Novel GPT J 6B F16 Marisa
Repository 🤗	https://huggingface.co/tsukemono/japanese-novel-gpt-j-6b-f16-marisa
Model Size	6b
Required VRAM	12.2 GB
Updated	2026-06-27
Maintainer	tsukemono
Model Type	gptj
Model Files	5.0 GB: 1-of-3 5.0 GB: 2-of-3 2.2 GB: 3-of-3
Supported Languages	ja
Quantization Type	fp16
Model Architecture	GPTJForCausalLM
Transformers Version	4.32.1
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	50400
Torch Data Type	float16
Activation Function	gelu_new

Rank the Japanese Novel GPT J 6B F16 Marisa 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 Japanese Novel GPT J 6B F16 Marisa

Best Alternatives	Context / RAM	Downloads	Likes
Model	0K / 6.2 GB	11	0
...oduct NER GPT J 6B 4bit Merged	0K / 2.5 GB	12	0
Kakaobrain Kogpt 6B 8bit	0K / 6.7 GB	5	2
GPT J 6B Skein 4bit 128g	0K / 4 GB	13	1
Pygmalion 6b Dev 4bit 128g	0K / 4 GB	8	121
GPT J 6B Alpaca Gpt4	0K / 24.3 GB	46	20
Pygmalion 6B 4bit 128g	0K / 4 GB	13	3
Dolly Shygmalion 6B 4bit 128g	0K / 4 GB	14	5
Pygmalion 6B 4bit 128g	0K / 4 GB	17	40
...O Pygway V8p4 Dev 6B 4bit 128g	0K / 4 GB	8	2

Note: green Score (e.g. "73.2") means that the model is better than tsukemono/japanese-novel-gpt-j-6b-f16-marisa.