> For the complete documentation index, see [llms.txt](https://unsloth.ai/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://unsloth.ai/docs/jp/moderu/tutorials.md). # 大規模言語モデル（LLM）チュートリアル最新のLLMを見つけ、モデルをローカルで実行・ファインチューニングして最適な性能を引き出す方法を学ぶ [Unsloth](https://github.com/unslothai/unsloth).

	カバー画像
Qwen3.8-Flash-Next	qwen38 flash new logo.png	Qwen3.8-Flash-Next
GLM-5.3-Flash	glm 5.3 flash.png	GLM-5.3-Flash
Qwen3.8	qwen3.8 logo.png	Qwen3.8-27B
GLM-5.3	glm 5.3 logo.png	GLM-5.3
Meta Muse Glimmer	Muse glimmer logo final.png	Meta Muse Glimmer
DeepSeek-V4-Pro-0813	deepseek v4 0813.png	DeepSeek-V4-Flash
DeepSeek-V4-0731	deepseekv4flash0731.png	DeepSeek-V4-Flash
GLM-5.3	glm 5.3 logo.png	GLM-5.3
Kimi K3	kimik3 logo.png	Kimi K3
GLM-5.2	glm52.png	GLM-5.2
Unsloth NVFP4	dynamic unsloth nvfp4.png	Unsloth Dynamic NVFP4
MTP ガイド	mtp final guide.png	Run MTP Models
DeepSeek-V4	deepseek v4 logo.png	DeepSeek-V4-Flash
Unsloth スタート	unsloth start logo.png	Unsloth Start
DiffusionGemma	diffusion gemma final logo.png	DiffusionGemma
Inkling-Small	inkling small.png	Inkling
インクリング	inklinggg.png	Inkling
AMD 向け Unsloth	AMD promo pic 1920.png	AMD
Kimi K2.7 Code	kimi k27 code font.png	Kimi K2.7 Code
Gemma 4 QAT	gemma 4 qat quant.png	Gemma 4 QAT
MiniMax M3	minimaxm3.png	MiniMax M3
Qwen3.6 MTP	qwen3.6 mtp logo.png	Qwen3.6
Qwen3.6	qwen3.6 logo.png	Qwen3.6
Gemma 4	Gemma 4 landscape.png	Gemma 4
Unsloth API エンドポイント	unsloth api long logo.png	Unsloth API
NVIDIA Nemotron 3 Ultra	nemotron ultra logo.png
Nemotron 3 Nano Omni	nvidia nemotron 3 nano omni.png	NVIDIA Nemotron 3 Omni
Kimi K2.6	kimi k26.png	Kimi K2.6
Qwen3.5	qwen35.png	Qwen3.5
Mistral 3.5	mistral3.5 logo.png	Mistral 3.5
GLM-5.1	glm51 logo.png	GLM-5.1
Granite 4.1	granite4.1 logo.png	IBM Granite 4.1
MiniMax-2.7	m27.png	MiniMax-M2.7
Unsloth Studio: LLM を実行 + 学習	unsloth studio logo only.png	Get Started
NVIDIA-Nemotron-3	nemotron 3 logo.png	NVIDIA Nemotron 3 Super
GLM-5	glm 5 logo.png	GLM-5
Claude Code	claude code white logo.png	Claude Code
OpenAI Codex	codex only logo.png	OpenAI Codex
MiniMax-2.5	minimax2.5 logo.png	MiniMax-M2.5
Qwen3-Coder-Next	qwen3-coder-next logo.png	Qwen3-Coder-Next
Kimi K2.5	kimi k25 logo.png	Kimi K2.5
DeepSeek-OCR 2	deepseekocr 2.png	DeepSeek-OCR 2
GLM-4.7-Flash	glm4.7flash.png	GLM-4.7-Flash
Qwen-Image-2512	QWEN-IMAGE-2512.png	Qwen-Image-2512
Nemotron 3	nemotron nano 3 promo.png	NVIDIA Nemotron 3
FunctionGemma	functiongemmaa.png	FunctionGemma
Qwen3-VL	qwen3-vl promo.png	Qwen3-VL
DeepSeek-OCR	deepseek ocr logo.png	DeepSeek-OCR
gpt-oss を実行	gpt-oss image.png	gpt-oss
Ministral 3	ministral 3 logo.png	Ministral 3
Kimi K2 Thinking	kimi k2 thinking logo.png	Kimi K2 Thinking
視覚強化学習	vision rl site.png	Vision RL
DeepSeek-V3.1 ターミナス	deepseek v3.1 logo.png	DeepSeek-V3.1
Qwen3 Coder	qwen3-coder 1920.png	Qwen3-Coder
gpt-oss をファインチューニング	sloth with comp.png	チュートリアル：gpt-ossをファインチューニングする方法
Magistral 1.2	magistral center.png	Magistral
Gemma 3n	Gemma 3 text only.png	Gemma 3n
Qwen3-2507	qwen3-2507.png	Qwen3-Next
DeepSeek-R1-0528	deepseek r1-0528.png	DeepSeek-R1-0528
Kimi K2	kimik2 landcsape.png	Kimi K2 Thinking
Devstral 2507	devstral logo.png	Devstral
Blackwell と RTX 50 GPU でファインチューニング	nvidia-logo-white background.png	Blackwell, RTX 50 and Unsloth
TTS のファインチューニング	tts finetuning landscape.png	Text-to-Speech Fine-tuning
Qwen3	qwen3.png	Qwen3
Phi-4 の推論	phi4 reasoning2.png	Phi-4 Reasoning
Dynamic 2.0 GGUF	dynamic v2 with unsloth.png	https://github.com/unslothai/docs/blob/main/basics/unsloth-dynamic-2.0-ggufs
Llama 4	llama 4 only.png	Llama 4
DeepSeek-V3-0324	v30324.png	DeepSeek-V3-0324
Grok 2	grok 2 logo.png	Grok 2
Gemma 3	gemma 3 logo.png	Gemma 3
QwQ-32B	qwq logo only.png	QwQ-32B
DeepSeek-R1	deepseek r1.png	DeepSeek-R1
強化学習（RL）	rl guide new.png	Tutorial: GRPO Training
Mistral Small 3.1	mistral small 3.1.png	https://www.unsloth.ai/blog/mistral-small-3.1
Llama 3	llama 3logo.png	Tutorial: Finetune Llama-3 and Use In Ollama
視覚のファインチューニング	llama_3.2_vision_large_rectangle_jPUNULJrVe5O4AvDDWO1M.webp	ビジョンのファインチューニング
継続事前学習	continued_pretraining_just_graph_HC0ALBypfCXyUUXClYPiN.webp	継続事前学習
Llama 3.3	llama_3.3_website_9hQURhj6KfZ7EnBRaKbiu.webp	https://unsloth.ai/blog/llama3-3
Gemma 2	gemma_2_long_OKsRGiTB8vrcIyXNWdgMw.avif	https://unsloth.ai/blog/gemma2
Phi-3	phi3_unsloth_ynBY7FG3NTjIbS11ozN_g.webp	https://unsloth.ai/blog/phi3

--- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://unsloth.ai/docs/jp/moderu/tutorials.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.