2025年3月21日現在
対話型 AIチャットWebサービス
ChatGPT
Just a moment...
claude

Claude
Talk with Claude, an AI assistant from Anthropic
Gemini

Gemini と話してアイデアを広げよう
Bard が Gemini になりました。Google AI で文章やリストの作成、計画の立案、新しい知識の習得など、さまざまなことができます。
copilot

Microsoft Copilot: あなたの AI アシスタントです
Microsoft Copilot は、情報、娯楽、アイデアを提供するあなたのアシスタントです。アドバイス、フィードバック、簡単な回答を得ることができます。今すぐ Copilot をお試しください。
DeepSeek
Just a moment...
perplexity
Just a moment...
Grok

Welcome | xAI
xAI is an AI company with the mission of advancing scientific discovery and gaining a deeper understanding of our univer...
対話型 AIチャットローカル
Ollama

Ollama
Get up and running with large language models.
llama.cpp
GitHub - ggml-org/llama.cpp: LLM inference in C/C++
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
LM Studio

LM Studio - Discover, download, and run local LLMs
Run Llama, Gemma 3, DeepSeek locally on your computer.
Text generation web UI
https://github.com/oobabooga/text-generation-webui
GPT4All
GitHub - nomic-ai/gpt4all: GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use. - nomic-ai/gpt4all
koboldcpp
GitHub - LostRuins/koboldcpp: Run GGUF models easily with a KoboldAI UI. One File. Zero Install.
Run GGUF models easily with a KoboldAI UI. One File. Zero Install. - LostRuins/koboldcpp
vLLM
GitHub - vllm-project/vllm: A high-throughput and memory-efficient inference and serving engine for LLMs
A high-throughput and memory-efficient inference and serving engine for LLMs - vllm-project/vllm
ローカル画像キャプション生成
BLIP
GitHub - salesforce/BLIP: PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generatio...
LLaVA
GitHub - haotian-liu/LLaVA: [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond. - haotian-liu/LLaVA
コメント