gpt-oss Local Deployment Guide: Run gpt-oss-20b and gpt-oss-120b with Ollama and llama.cpp
gpt-oss local deployment with Ollama and llama.cpp: official memory needs for 20b and 120b, MXFP4, MoE offload flags, and reasoning effort.
-
-
Ollama 下载慢怎么办：模型路径修改与国内加速方法（2026）
Ollama 下载慢怎么办？先排查代理与断点续传，再用 OLLAMA_MODELS 改模型路径、从魔搭拉 GGUF，附三大系统步骤。
-
Gemma 本地部署教程：用 Ollama 运行 Gemma 4 与 Gemma 3，按显存选版本
Gemma 本地部署教程：用 Ollama 运行 Gemma 4 与 3，对照 e2b、e4b、12b、26b、31b 的体积与上下文，按显存选版本，附思考模式与排错。
-
gpt-oss 本地部署教程：用 Ollama 与 llama.cpp 运行 gpt-oss-20b 和 gpt-oss-120b
gpt-oss 本地部署教程：用 Ollama 与 llama.cpp 运行 20b 和 120b，对照官方内存需求、MXFP4 量化、MoE 卸载参数与推理强度设置。
-
本地大模型编程助手：用 Ollama、Continue 和 Qwen Coder 搭建私有代码助手（2026）
本地大模型编程怎么搭：Ollama 加 Continue 扩展，按显存选 Qwen Coder 版本，补全、聊天、智能体分工，以及上下文长度与速度的常见坑。
-
本地知识库搭建（RAG）：Ollama + Open WebUI / AnythingLLM 实战
本地知识库搭建怎么做？用 Ollama 配 Open WebUI 或 AnythingLLM 做 RAG：嵌入模型、切块、上下文长度与常见坑，数据全程留在本机。
-
How to Run DeepSeek Locally: Distilled vs Full Model, Picked by VRAM
Run DeepSeek locally the right way: R1 distills vs the full model vs V4, which Ollama tag fits 8GB to 48GB of VRAM, and four commands to get started.
-
LLM Quantization Explained: What Q4_K_M Means and How to Choose a GGUF Quant
LLM quantization explained: what Q4_K_M means, GGUF quant sizes and speeds side by side, and how to pick Q4, Q5 or Q8 for your VRAM, with Ollama commands.
-
LM Studio Tutorial: Download and Run Models Without the Command Line
A complete LM Studio tutorial: install, search and download models, pick a quantization, tune context, chat with documents and start the local API.
-
How to Run an LLM Locally: Hardware You Need and How to Pick a Model (2026)
Want to run an LLM locally? Learn how much VRAM you need, which models fit 8GB to 48GB, and how to get your first model running with Ollama in five steps.
