🍥

记录并分享日常

Tags

58 pages

Local LLM

Run Bonsai Locally on Windows: 1-bit Models, Vision, and MCP Tool Calls

Is the CMP 170HX 80GB Memory Unlock Reliable? AI Mining GPU Buying Risks and Checklist

How to deploy Ollama OpenClaw locally: model selection, port, permissions and memory plug-in troubleshooting

TencentDB Agent Memory local deployment tutorial: long-term memory, log compression and traceable recall

How to calculate the cost of running Agent on a consumer-grade graphics card: electricity bill, depreciation and cost per task

Windows WSL deployment of local Agent tutorial: Ollama, Codex OSS and permission control

Whether the Ollama performance of NAS deployment is insufficient: how to judge the CPU, memory and graphics card

Local large model API for Codex usage tutorial: Ollama, LM Studio and vLLM

What to do if vLLM KV Cache has insufficient memory: video memory, context and concurrency troubleshooting

How to use LM Studio OpenAI compatible interface: Local API access tutorial

How to configure Ollama multi-model switching: resident, video memory and Modelfile tutorials

RTX 3060 runs the best quantized version of Qwen3: how to choose 12GB video memory

Common Codex + Ollama local model errors: troubleshooting order, causes, and fixes

Common Errors When Connecting Codex to Ollama Local Models: Tutorial, Troubleshooting, and FAQ

How to Use Chatbox: Connect OpenAI, Claude, and Ollama in an Open-Source AI Desktop Client

Qwythos-9B 1M Context: Run with vLLM, SGLang, or Transformers

GTX 1060 Running Qwen 35B: Optimizing llama.cpp from 3 tok/s to 17 tok/s

GLM 5.2 Goes Open Source: Million-Token Context, Agent Coding, and the Cost of Local Deployment

Codex CLI with Ollama or LM Studio: OSS Mode Setup Guide

Holo 3.1 Local Deployment Guide: Run a Computer Use Agent with llama.cpp and OpenClaw

Hermes Agent Desktop Guide: Install on Windows, macOS, Linux and Connect Local Models

Headroom Setup Guide: Compress AI Agent Context and Token Use

How to Use Gemma 4 12B: Hugging Face Model Card and Local Loading Guide

Can Gemma 4 12B Run Locally? 16GB PC Trial and Getting Started Notes

Ollama Connects to Codex App: How Local LLMs Become AI Coding Agents

RTX 3060 12GB + Qwen3.6 35B: llama.cpp --n-cpu-moe Setup

Qwen3.6-35B-A3B jailbreak local deployment: uncensored GGUF, llama.cpp, and safety boundaries

Running Qwen3.6-35B Locally on an RTX 3070 8GB: llama.cpp Deployment Notes and Tuning Parameters

llama.cpp b9196 Update: Windows Prebuilt Binaries Support CUDA 13.1, Vulkan, HIP, and SYCL

Claude Code Ollama Setup: Run Local Models Through CC Switch

Running DeepSeek 4 Locally: Antirez's ds4 Experiment on Apple Silicon Mac

llama.cpp Multi-GPU: 2 GPUs vs 1, tensor-split, and VRAM

RTX 5090 / 5080 AI Inference Benchmarks: Choosing for Local LLMs, 4K Video, and Real-Time 3D

DeepSeek V4 Local Private Deployment: Choosing Domestic Chips or Consumer GPU Clusters

Best Local LLMs for RTX 3060 12GB: Models, GGUF, and VRAM Limits

Hermes Agent + Qwen3.6 Local Setup: WSL2, llama.cpp, CUDA, and GGUF

NVIDIA Releases Nemotron 3 Nano Omni: An Open Omnimodal Reasoning Model for Agents

Qwen3.6 VRAM Requirements: 27B and 35B-A3B GGUF Table

DeepSeek V4 VRAM Requirements: Pro vs Flash Quantization Table

Gemma 4 VRAM Requirements: E2B, E4B, 26B, and 31B GGUF

llama.cpp 8GB VRAM Guide: 32K vs 64K Context and KV Cache Settings

A 16GB GPU Can Still Run 35B Models: VRAM Compression Strategies for MoE Models in LM Studio

Ollama Multi-GPU: Does VRAM Pool? GPU Selection and Performance

Gemma 4 E4B Uncensored vs Official: Safety, Behavior, License, and Local Use

How to Use llama-quantize for GGUF Models

Download GGUF Models from Hugging Face with llama.cpp

What Does `it` Mean in Gemma-4-31B-it

Llama GGUF Quantization Guide: Choose Q4_K_M, Q5_K_M, Q6_K, or Q8_0

How to Access a Local Ollama API Over LAN on Windows

Gemma 4 Local Runtime Guide: From One-Command Start to Dev Integration