ModemGuides · The Blog · Tagged: Ollama
Ollama
Best Local AI Models by VRAM and Memory: 8GB to 512GB (2026)Find your memory number and get the one verified pick for it. Six tiers from a 12GB card to a 512GB Mac Studio, every size sourced from the...
Can You Run GLM-5.3-Flash Locally? The 128GB Reality CheckGLM-5.3-Flash lands at 320B with 18B active under MIT. The honest hardware math: GGUF sizes, the 128GB line, and day-one runtime status.
Run DeepSeek V4-Flash Locally: Hardware Requirements 2026The 0731 weights are out and the tier map is current: 103GB build on mainline llama.cpp, LM Studio gone local, and the M5 Mac Studio math.
Local AI Hardware in 2026: GPUs, VRAM, and Honest Build Tiers for the Memory-Shortage EraWhich GPU and how much VRAM for local AI in 2026 — honest build tiers repriced for the memory shortage, from used RTX 3090 to Apple Silicon.
The Mac Studio M5 Ultra Is Official: What 512GB Actually Runs, and Who Should Buy OneApple's Mac Studio M5 Ultra is official: 512GB max, not 768GB. Which local AI models fit, the cluster math, and whether to buy, wait, or skip.
Has Open-Source AI Actually Caught Up? The 2026 Reality CheckOpen models now sit in the frontier top five, but half the viral scoreboard is unshipped. The verified ledger, the price math, and what runs at home.
The AI Compute Wall: Power, Chips, and Why Owning Your AI Stack Is the HedgeThe viral RAND chart, explained without the geopolitics: why AI's power and chip limits are already raising your costs, and the local-first hedge.
Self-Verifying AI Agent Loops: What's Real, What's Hype, and How to Run OneA self-verifying AI agent loop checks its own work against live sources. Here is the real technique behind the viral Kimi swarm, minus the hype.
The Ryzen AI Max+ 395 for Local LLMs: An Honest Reality CheckThe honest tokens-per-second, the $1,499-vs-$2,200 SKU trap, the Linux memory unlock, and whether a Strix Halo box can replace your Claude Code bill.
Local LLM Knowledge Base in Obsidian: Setup GuideAndrej Karpathy's LLM Wiki pattern lets an AI build and maintain a structured knowledge base from your documents. Here's how to set it up locally with Obsidian and...
Self-Improving AI Agents Are Here: What AutoAgent Means for Your Local AI StackAutoAgent proves AI agents can autonomously modify their own tools and behavior. What self-improving agents mean for your local AI stack and home network security.
How to Build a Local AI Knowledge Base You Actually OwnBuild a private, local-first AI knowledge base using Obsidian, Ollama, and AnythingLLM. Your research stays on your network with zero monthly fees.
Network Security for Local AI: How to Isolate, Harden, and Protect Your Home AI DeploymentsRunning AI locally keeps your data private, but default configurations can leave your home network vulnerable. Learn how to protect your deployment from exposed APIs, prompt injection, and...