10

Large Language Models (LLMs) and ChatGPT-related

10.1 LLM Development Projects

In recent years, the development of large language models supporting Japanese has been increasingly active, with multiple large-scale projects underway.

LLM-jp project: Outcomes of the LLM study group centered on the National Institute of Informatics (NII).

  • llm-jp-eval (Stars: 175): LLM automated evaluation tool
  • llm-jp-sft (Stars: 66): Supervised fine-tuning
  • llm-jp-tokenizer (Stars: 54): LLM tokenizer
  • llm-jp-corpus (Stars: 49): Training corpus
  • llm-jp-eval-mm (Stars: 44): Multimodal LLM evaluation
  • llm-jp-judge (Stars: 64): Automated generation evaluation
  • llm-jp-vila (Stars: 10): VILA-based VLM training

Swallow Project: A Japanese LLM development project centered on Tokyo Institute of Technology.

  • swallow-evaluation (Stars: 26): Evaluation scripts
  • swallow-evaluation-instruct (Stars: 34): Post-training model evaluation
  • swallow-corpus (Stars not listed): Large-scale Japanese web corpus

shisa-v2 (shisa-ai/shisa-v2): A Japanese/English bilingual LLM. Stars: 35.

OneCompression (FujitsuResearch/OneCompression, Stars: 445): A post-training quantization (PTQ) pipeline for LLMs developed by Fujitsu Laboratories. It integrates QEP (NeurIPS 2025), ILP mixed precision, rotation preprocessing, and a vLLM plugin — a comprehensive framework for efficient local LLM inference.

llm-jp-eval
LLM automated evaluation tool
175
llm-jp-sft
Supervised fine-tuning
66
llm-jp-tokenizer
LLM tokenizer
54
llm-jp-corpus
Training corpus
49
llm-jp-eval-mm
Multimodal LLM evaluation
44
llm-jp-judge
Automated generation evaluation
64
llm-jp-vila
VILA-based VLM training
10
swallow-evaluation
Evaluation scripts
26
swallow-evaluation-instruct
Post-training model evaluation
34
shisa-v2
shisa-v2 (shisa-ai/shisa-v2): A Japanese/English bilingual LLM. Stars: 35.
35
OneCompression
OneCompression (FujitsuResearch/OneCompression, Stars: 445): A post-training quantization (PTQ) pipeline for LLMs developed by Fujitsu Laboratories. It integrates QEP (NeurIPS 2025), ILP mixed precision, rotation preprocessing, and a vLLM plugin — a comprehensive framework for efficient local LLM inference.
445

Japanese LLMs on Hugging Face

In the text-generation category on Hugging Face, numerous Japanese LLMs have been published. The models with the highest download counts are shown below.

Model HF DL Likes Developer Description
llm-jp-4.1-8b-thinking 80k 18 NII/LLM-jp 8B reasoning model from the llm-jp-4.1 series
llm-jp-4-8b-instruct 49k 16 NII/LLM-jp Instruction-tuned 8B model from llm-jp-4 series
sarashina2.2-3b-instruct-v0.1 16k 39 SB Intuitions Autoregressive Japanese model
Llama-3-Swallow-8B-Instruct-v0.1 9k 21 Tokyo Institute of Technology Meta Llama 3 Japanese extension
Llama-3.1-Swallow-8B-Instruct-v0.5 7k 20 Tokyo Institute of Technology Trained on synthetic Japanese data
Mistral-Nemo-Japanese-Instruct-2408 6k 49 CyberAgent Japanese version of Mistral-Nemo
LFM2.5-1.2B-JP-202606 4k 82 Liquid AI Hybrid architecture
Llama-3-ELYZA-JP-8B 4k 150 ELYZA High popularity with 150 Likes
llm-jp-4-8b-thinking 3k 52 NII/LLM-jp 8B model with reasoning trace generation
NVIDIA-Nemotron-Nano-9B-v2-Japanese 3k 146 NVIDIA Mamba-2/MLP/Attention mixture
llm-jp-4-32b-a3b-thinking 2k 40 NII/LLM-jp 32B MoE reasoning model
TinySwallow-1.5B-Instruct 2k 61 Sakana AI Lightweight model via TAID distillation

The shift toward reasoning (thinking) models continues. The newly released llm-jp-4.1-8b-thinking (80k/week) now tops this table, and the GGUF build llm-jp-4-33b-thinking-gguf (271k/week, #10 across all Japanese NLP models on Hugging Face) has also grown sharply. Meanwhile, the previous leaders llm-jp-4-8b-thinking (21k→3k/week) and llm-jp-4-32b-a3b-thinking (16k→2k/week) declined as the 4.1 series arrived, while the instruction-tuned llm-jp-4-8b-instruct (49k/week) holds steady. NVIDIA-Nemotron-Nano-9B-v2-Japanese stays at 3k/week, though its 146 Likes remain high.

The Swallow project is also extremely active on Hugging Face, extending diverse base models such as Llama 3/3.1, Gemma 2, GPT-OSS, and Qwen3 to Japanese. In particular, GPT-OSS-Swallow provides large-scale models of 20B and 120B parameters, reinforcing Japanese capabilities while maintaining math and coding performance.

The ELYZA series receives strong community support with high Like counts (Llama-3-ELYZA-JP-8B: 150 Likes, ELYZA-japanese-Llama-2-7b-instruct: 75 Likes).

TinySwallow-1.5B (Sakana AI) is a model distilled from Qwen2.5-32B-Instruct using TAID distillation technology, demonstrating the potential of compact yet high-performance Japanese models.

LFM2.5-1.2B-JP (Liquid AI): Adopts a hybrid architecture combining Mamba-2 and MLP, achieving JMMLU 50.7, M-IFEval 58.1, and GSM8K 56.0. The June 2026 release (LFM2.5-1.2B-JP-202606) reaches 4k/week (82 Likes) and is also distributed in ONNX and GGUF formats; the GGUF build sees 8k/week, more than the original.

llm-jp-4.1-8b-thinking
8B reasoning model from the llm-jp-4.1 series
80k 18
llm-jp-4-8b-instruct
Instruction-tuned 8B model from llm-jp-4 series
49k 16
sarashina2.2-3b-instruct-v0.1
Autoregressive Japanese model
16k 39
Llama-3-Swallow-8B-Instruct-v0.1
Meta Llama 3 Japanese extension
9k 21
Llama-3.1-Swallow-8B-Instruct-v0.5
Trained on synthetic Japanese data
7k 20
Mistral-Nemo-Japanese-Instruct-2408
Japanese version of Mistral-Nemo
6k 49
LFM2.5-1.2B-JP-202606
Hybrid architecture
4k 82
Llama-3-ELYZA-JP-8B
High popularity with 150 Likes
4k 150
llm-jp-4-8b-thinking
8B model with reasoning trace generation
3k 52
NVIDIA-Nemotron-Nano-9B-v2-Japanese
Mamba-2/MLP/Attention mixture
3k 146
llm-jp-4-32b-a3b-thinking
32B MoE reasoning model
2k 40
TinySwallow-1.5B-Instruct
Lightweight model via TAID distillation
2k 61
LFM2.5-1.2B-JP
LFM2.5-1.2B-JP (Liquid AI): Adopts a hybrid architecture combining Mamba-2 and MLP, achieving JMMLU 50.7, M-IFEval 58.1, and GSM8K 56.0. The June 2026 release (LFM2.5-1.2B-JP-202606) reaches 4k/week (82 Likes) and is also distributed in ONNX and GGUF formats; the GGUF build sees 8k/week, more than the original.

10.2 ChatGPT/LLM Applications

Japanese applications of ChatGPT and LLMs span a wide range.

Dialogue / Chatbots:

  • ChatdollKit (Stars: 1,300): A Unity toolkit for turning 3D models into chatbots
  • aiavatarkit (Stars: 704): Building AI-based conversational avatars
  • chatvrm (Stars: 848): A VRM character conversation demo by pixiv

VTubers / Virtual Characters:

  • gptuber-by-langchain (Stars: 63): A system where GPT acts as a YouTuber
  • VRChatGPT (Stars: 15): Conversation on VRChat
  • AITuberDegikkoMirii (Stars: 5): AITuber platform

RAG (Retrieval Augmented Generation):

  • RAG-Japanese / rag-japanese (Stars: 10): RAG for Japanese LLMs
  • azure-search-openai-demo (Stars: 46): Japanese implementation of the RAG pattern
  • wikipedia-japanese-open-rag: RAG with Japanese Wikipedia

Prompt Engineering:

  • chatgpt-prompt-sample-japanese (Stars: 431): Japanese prompt samples
ChatdollKit
A Unity toolkit for turning 3D models into chatbots
1.3k
aiavatarkit
Building AI-based conversational avatars
704
chatvrm
A VRM character conversation demo by pixiv
848
gptuber-by-langchain
A system where GPT acts as a YouTuber
63
VRChatGPT
Conversation on VRChat
15
AITuberDegikkoMirii
AITuber platform
5
azure-search-openai-demo
Japanese implementation of the RAG pattern
46
chatgpt-prompt-sample-japanese
Japanese prompt samples
431

10.3 Evaluation Benchmarks

  • IgakuQA (Stars: 52): GPT-4/ChatGPT evaluation on the Japanese medical licensing exam
  • Japanese-RP-Bench: Japanese role-playing ability benchmark
  • japanese-llm-roleplay-benchmark (Stars: 42): LLM character role-play evaluation
  • pfmt-bench-fin-ja (Stars: 9): Japanese financial benchmark
  • igakuqa119 (Stars: 10): LLM evaluation on the 119th Japanese medical licensing exam
  • jmle2026-bench (Stars: 11): LLM benchmark on the 120th Japanese Medical Licensing Examination (Feb 2026)
  • japanese-hr-niah (kufu): Long-context LLM evaluation in the Japanese HR/labor domain using Needle-In-A-Haystack format
  • Doppelganger-JC: Benchmark for cross-lingual homograph misuse between Chinese and Japanese in LLMs
  • JMultiWOZ-TC (llm-jp): Agent Function Calling evaluation in multi-turn dialogue scenarios

IgakuQA
GPT-4/ChatGPT evaluation on the Japanese medical licensing exam
52
japanese-llm-roleplay-benchmark
LLM character role-play evaluation
42
pfmt-bench-fin-ja
Japanese financial benchmark
9
igakuqa119
LLM evaluation on the 119th Japanese medical licensing exam
10
jmle2026-bench
LLM benchmark on the 120th Japanese Medical Licensing Examination (Feb 2026)
11