होम / Local LLMs with Ollama & llama.cpp · English Local LLMs with Ollama & llama.cpp
Run open-weight LLMs on your own machine with Ollama and llama.cpp: GGUF, quantization, APIs, RAG, tool calling, tuning and security.
Local LLMs with Ollama & llama.cpp Hindi mein seekhein — free Local LLMs with Ollama & llama.cpp tutorial in Hindi, lessons, shorts aur interview questions ke saath.
कोर्स शुरू करें → · इंटरव्यू प्रश्न
30 पाठ · 10 मॉड्यूल · मुफ़्त
आप क्या सीखेंगे Explain how local inference works: tokens, prefill and decode, the KV cache and why memory bandwidth limits speed. Choose a model family, size and GGUF quantization level that fits your RAM or VRAM and your task. Run and customize models with the Ollama CLI, Modelfiles, sampling parameters and chat templates. Call local models from code through the Ollama REST API, its Python library and OpenAI-compatible endpoints. Build and serve models directly with llama.cpp, llama-cli and llama-server. Build structured-output, RAG and tool-calling applications that run fully offline. Tune memory, GPU offload and concurrency, and deploy a local LLM server securely. पाठ्यक्रम Why Run LLMs Locally What Local LLMs Are and Why They Matter The Mental Model: Tokens, Weights and Inference Hardware Basics: RAM, VRAM and Bandwidth Model Files, GGUF and Quantization Weights, Parameters and Model Families The GGUF File Format Quantization Levels and Trade-offs Getting Started with Ollama Installing Ollama and the Server Model Everyday Ollama CLI Commands Choosing Models from the Library Customizing Models with Modelfiles Modelfile Basics: FROM, SYSTEM and PARAMETER Sampling Parameters: Temperature, top_p and Friends Chat Templates and Special Tokens Programming Against the Ollama API The REST API: generate, chat and streaming The Official Python Library OpenAI-Compatible Endpoints Working Directly with llama.cpp What llama.cpp Is and How to Build It llama-cli and the Core Flags llama-server: HTTP, Web UI and Parallel Slots Building Applications on Local Models Structured Output with JSON Schemas Embeddings and Local RAG Tool Calling with Local Models Performance Tuning and Memory Memory Math: Weights plus KV Cache GPU Offload and CPU/GPU Splits Context, Keep-Alive and Concurrency Settings Deployment, Security and Pitfalls Running Local LLMs in Docker and on a Team Server Securing Local Inference Common Pitfalls and Evaluating Quality Revision and Interview Prep Cheat Sheet: Local LLMs in One Page Common Interview and Exam Questions Mixed Self-Check