Local models
Running models on your own hardware: Ollama, llama.cpp, open weights and on-device AI
Latest stories See all →
- We Taught AI to Answer Questions. Who Taught It to Change Its Mind?
- Open-Weight vs Closed-Weight Models: What's the Difference?
- Sovereign Decisions: Open-weight Jev Alternatives in Solace Agent Mesh
- A compact conversational language model that chats in plain English and writes Python
- Open-weight model GLM 5.3 built full Firefox exploit chains with zero human input in under 48 hours
- Why Self-Hosted GLM-5.3 Needs 8 GPUs, Not 4, for Long Coding Sessions
- NVIDIA Nemotron 3.5 Transcribe: A Complete Guide to the Speech AI Model
- Edge0 Releases Audio8-TTS-Realistic, a 0.6B Voice Cloning TTS Model
- How to Run Sage A1.5 Locally with llama.cpp
- From Prompt to Edge AI — Hackathon Participants Create Mobile Apps in Less Than An Hour
- I Studied a 16 GB GPU Test, and It Changed How I See Local AI
- Raspberry Pi 5 AI Module Case with Camera Mount – AI HAT All-in-One Setup #3DThursday #3DPrinting
- ASRock Industrial AI Box-A395 Review: Taking Strix Halo to Work
- How Edge AI Is Rewriting Embedded System Architectures
- Mistral’s Large 4 open weights arrive with a 1-point coding lead over GLM-5.3: “There’s nothing you can’t do with this model that you can do with competitors.”
- LFM3–1.7B : Best Small LLM is here
- Nemotron 3.5 Transcribe: What It Is, How Accurate It Is, and How to Run It
- 5 Docker Containers You Need for a Home AI Lab
- NVIDIA Releases Nemotron 3.5 Transcribe: An Open 30B MoE Model for 40-Language Transcription with ~4B Active Parameters
- Xerxes Home Lab adds Jetson support, NVMe, and PoE
- LUMEN: An AI Neonatal Specialist That Works When the Network Doesn't
- How to Run Clover-35B-A3B-Preview Locally with SGLang
- Self-Hosted AI on a Raspberry Pi: A Complete 2026 Deployment Guide
- Mistral releases open weights for Large 4, MaaS use needs a license
Videos
- This 2B Voice AI Runs LOCALLY at 158ms — CRAZY Fast, WILD Mistakes (llama.cpp Realtime Test)
- d3 is a new Ollama model that Makes DECISIONS (500 Messages in 23 Seconds!) - d3 on a Laptop GPU
- They Shrunk a 54GB AI Model to 8GB... It Got BETTER?! #localai #qwen #ai
- Mac Studio M5 Ultra Review for Local LLMs: LM Studio vs oMLX vs TensorFold
- Forget Ollama... Use Magnitude For Local AI
- Control Any Smart TV with Free Local AI Agent (Hermes + Ollama)
- 7 Free Engines That Run Local AI 2x Faster Than llama.cpp
- Strata Metal Hits 107 TPS on M5 Max — 4× Faster Than LM Studio!
- MiniCPM-V 4.7 1B: Install with Ollama and llama.cpp, Then Push It to the Limit
- Deploy AI agents on Kubernetes: Move from Ollama to vLLM
- CodeAF with Ollama: Coding Agent Factory Tested Locally
- Strata vs Llama.cpp vs vLLM
Podcasts
Recent episodes
- The AI Boom Is Impressive. Can It Last?
- Srsly Risky Biz: Chinese AI can learn to love the West
- WW 1007: A Sea of Blues and Greens - Another Round of Buyout Offers Sent to Microsoft's Workforce
- Episode 421: Nvidia "Manufactured" GPU Crisis, Our Local AI Testing & More
- Do the models you use have an AI bill of materials? | CIQ’s Gregory Kurtzer
- 1050 - Everyone Is Hacking Their TV
- 1050 - Everyone Is Hacking Their TV
- Podcast: Kimi K3.1 Pro, the new cyber reality, and Muse musings
- IM 893: It All Comes Back to Cats - From Academic Papers to 1.2 Million Startup Ideas
- WW 1006: Are You Lying to Me Now, Paul? - OmniBook Ultra 16, ProArt P16, & Lenovo Pro 9n Impressions
- D2DO316: Local AI Foundations
- The Future of Web Apps: Will AI Agents Generate UIs on the Fly?