What are the hardware requirements for Japanese GPT Neox 3.6B Instruction Sft V2?

Japanese GPT Neox 3.6B Instruction Sft V2 requires approximately 7.4 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 GPT Neox 3.6B Instruction Sft V2 and how large is it?

Japanese GPT Neox 3.6B Instruction Sft V2 is developed by rinna, 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 GPT Neox 3.6B Instruction Sft V2?

Japanese GPT Neox 3.6B Instruction Sft V2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Japanese GPT Neox 3.6B Instruction Sft V2 by rinna — VRAM 7.4GB, 2K context

Name: Japanese GPT Neox 3.6B Instruction Sft V2
Author: rinna

Japanese GPT Neox 3.6B Instruction Sft V2 is an open-source language model by rinna. Features: 3.6b LLM, VRAM: 7.4GB, Context: 2K, License: mit, Instruction-Based, LLM Explorer Score: 0.08.

Arxiv:2404.01657 Base model:finetune:rinna/japa... Base model:rinna/japanese-gpt-... Dataset:anthropic/hh-rlhf Dataset:stanfordnlp/shp Gpt neox Instruct Ja Lm Pytorch Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/rinna/japanese-gpt-neox-3.6b-instruction-sft-v2

Japanese GPT Neox 3.6B Instruction Sft V2 Parameters and Internals

Model Type

text generation

Supported Languages

Japanese (Advanced)

Training Details

Data Sources:

Anthropic/hh-rlhf, stanfordnlp/SHP

Methodology:

Finetuning using translated subsets of datasets.

Model Architecture:

A 36-layer, 2816-hidden-size transformer-based language model.

Input Output

Input Format:

A special format for constructing inputs as a conversation between 'ユーザー' and 'システム'.

LLM Name	Japanese GPT Neox 3.6B Instruction Sft V2
Repository 🤗	https://huggingface.co/rinna/japanese-gpt-neox-3.6b-instruction-sft-v2
Base Model(s)	rinna/japanese-gpt-neox-3.6b rinna/japanese-gpt-neox-3.6b
Model Size	3.6b
Required VRAM	7.4 GB
Updated	2026-07-03
Maintainer	rinna
Model Type	gpt_neox
Instruction-Based	Yes
Model Files	7.4 GB 7.4 GB
Supported Languages	ja
Model Architecture	GPTNeoXForCausalLM
License	mit
Context Length	2048
Model Max Length	2048
Tokenizer Class	T5Tokenizer
Padding Token	[PAD]
Vocabulary Size	32000
Torch Data Type	float16

Rank the Japanese GPT Neox 3.6B Instruction Sft V2 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 GPT Neox 3.6B Instruction Sft V2

Best Alternatives	Context / RAM	Downloads	Likes
...rrowSmartPlus 3.6B Instruction	2K / 14.3 GB	9	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
...tion Sft 8bit 1g Actorder True	2K / 2.8 GB	51	3
...n Sft 4bit 128g Actorder False	2K / 2.1 GB	8	2

Note: green Score (e.g. "73.2") means that the model is better than rinna/japanese-gpt-neox-3.6b-instruction-sft-v2.