What are the hardware requirements for Japanese Large Lm 3.6B?

Japanese Large Lm 3.6B requires approximately 7.2 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Japanese Large Lm 3.6B and how large is it?

Japanese Large Lm 3.6B is developed by line-corporation, a model with 3.6b 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 Large Lm 3.6B?

Japanese Large Lm 3.6B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Japanese Large Lm 3.6B by line-corporation — VRAM 7.2GB, 2K context

Name: Japanese Large Lm 3.6B
Author: line-corporation

Japanese Large Lm 3.6B is an open-source language model by line-corporation. Features: 3.6b LLM, VRAM: 7.2GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.08.

Dataset:cc100 Dataset:mc4 Dataset:oscar Dataset:wikipedia Deploy:azure Endpoints compatible Gpt neox Ja Pytorch Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/line-corporation/japanese-large-lm-3.6b

Japanese Large Lm 3.6B Parameters and Internals

Model Type

text generation, Japanese language model

Use Cases

Areas:

Research, Commercial applications

Applications:

Text generation, Japanese language applications

Primary Use Cases:

Japanese text generation, Japanese language applications

Additional Notes

Uses a sentencepiece tokenizer with a unigram language model and byte-fallback. Does not apply pre-tokenization.

Supported Languages

ja (high proficiency)

Training Details

Data Sources:

wikipedia, mc4, cc100, oscar, Web texts crawled by in-house system

Data Volume:

650 GB

Methodology:

Standard language model training

Model Architecture:

GPTNeoX with RoPE for position encoding

Input Output

Input Format:

Raw Japanese sentences

Accepted Modalities:

text

Output Format:

Generated text in Japanese

Performance Tips:

Use GPU for faster inference and setting the seed for reproducibility

LLM Name	Japanese Large Lm 3.6B
Repository 🤗	https://huggingface.co/line-corporation/japanese-large-lm-3.6b
Model Size	3.6b
Required VRAM	7.2 GB
Updated	2026-08-08
Maintainer	line-corporation
Model Type	gpt_neox
Model Files	7.2 GB 7.2 GB
Supported Languages	ja
Model Architecture	GPTNeoXForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.29.2
Tokenizer Class	T5Tokenizer
Padding Token	<pad>
Vocabulary Size	51200
Torch Data Type	float16

Rank the Japanese Large Lm 3.6B 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 Large Lm 3.6B

Best Alternatives	Context / RAM	Downloads	Likes
Japanese GPT Neox 3.6B	2K / 7.4 GB	7552	102
...y Jimba Japanese Large Lm 3.6B	2K / 7.1 GB	6	0
...rrowSmartPlus 3.6B Instruction	2K / 14.3 GB	9	1
...rrowSmartPlus 3.6B Instant Sft	2K / 14.3 GB	7	1
...rtPlus 3.6B Instant Sft JHSVer	2K / 14.3 GB	9	1
... GPT Neox 3.6B Instruction Sft	2K / 7.4 GB	9602	105
... GPT Neox 3.6B Instruction Ppo	2K / 7.4 GB	3052	74
... Large Lm 3.6B Instruction Sft	2K / 7.2 GB	127	27
...T Neox 3.6B Instruction Sft V2	2K / 7.4 GB	627	26
...tion Sft 8bit 1g Actorder True	2K / 2.8 GB	51	3

Note: green Score (e.g. "73.2") means that the model is better than line-corporation/japanese-large-lm-3.6b.