ollama-rag
Build RAG systems with Ollama local + cloud models. Latest cloud models include DeepSeek-V3.2 (GPT-5 level), Qwen3-Coder-480B (1M context), MiniMax-M2. Use for document Q&A, knowledge bases, and agentic RAG. Covers LangChain, LlamaIndex, ChromaDB, and embedding models.
npx skills add majiayu000/claude-skill-registry --skill ollama-rag --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Ollama RAG Guide Build RAG systems with Ollama - run locally or use cloud for massive models. ## Ollama Cloud Models (Dec 2025) Access via `ollama signin` (v0.12+). No local storage needed, privacy preserved. | Model | Params | Context | Best For | |-------|--------|---------|----------| | `deepseek-v3.2:cloud` | 671B | 160K | **GPT-5 level**, reasoning | | `deepseek-v3.1:671b-cloud` | 671B | 160K | Thinking + non-thinking hybrid | | `qwen3-coder:480b-cloud` | 480B | **256K-1M** | Agentic coding, repo-scale | | `minimax-m2:cloud` | 230B (10B active) | 128K | #1 open-source, tools | | `gpt-oss:120b-cloud` | 120B | 128K | OpenAI open weights | | `glm-4.6:cloud` | - | - | Code generation | ```bash # Sign in to access cloud ollama signin # Run cloud models ollama run deepseek-v3.2:cloud ollama run qwen3-coder:480b-cloud ollama run minimax-m2:cloud ``` ## Local Models (Dec 2025) ### Reasoning Models | Model | Params | Context | Best For | |-------|--------|---------|----------| | `nemotron-3-nano` | 30B (3.6B active) | **1M tokens** | Agents, long docs, code | | `deepseek-r1` | 7B-671B | 128K | Reasoning, math, code | | `qwq` | 32B | 32K | Logic, analysis | | `llama4` | 109B/400B | 12
- Ollama Cloud Models (Dec 2025)
- Local Models (Dec 2025)
- Reasoning Models
- Fast/Efficient Models
- Embedding Models
- Quick Start
- Cloud (No Local Resources)
- Local
- Stack Options
- Option A: LangChain + ChromaDB (Most Common)
- Option B: LlamaIndex (Better Accuracy)
- Option C: Direct Ollama API (Minimal Dependencies)
- Vector Database Options
- Nemotron 3 Nano Deep Dive
Sign in to access cloud ollama signin Run cloud models ollama run deepseek-v3.2:cloud ollama run qwen3-coder:480b-cloud ollama run minimax-m2:cloud ollama run deepseek-v3.2:cloud # GPT-5 level ollama run qwen3-coder:480b-cloud # 1M context for huge repos ollama pull nemotron-3-nano # 1M context, 24GB VRAM ollama pull snowflake-arctic-embed2
What does the ollama-rag skill do?
Build RAG systems with Ollama local + cloud models. Latest cloud models include DeepSeek-V3.2 (GPT-5 level), Qwen3-Coder-480B (1M context), MiniMax-M2. Use for document Q&A, knowledge bases, and agentic RAG. Covers LangChain, LlamaIndex, ChromaDB, and embedding models.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill ollama-rag --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.