📂 Self-Hosting
Find all our articles on Self-Hosting: tips, tutorials and practical guides to get the most out of AI.
Best Lm Studio Models (November 2026)
Best LM Studio models (November 2026): our pick of local models to download to get the most out of AI on your machine.
Ripple-65B Preview: a 65B-parameter agentic coding model under Apache 2.0 for $32M of compute
Ripple-65B Preview: the 65B parameter agentic coding model, open source under Apache 2.0, trained for only $32M in compute.
GAAC: compressing your local LLM's KV cache without losing a single bit
GAAC compresses your local LLM's KV cache losslessly: discover this approach with no compromise on accuracy for local inference.
vLLM 0.32.0: eight CVEs at once, including one allowing code execution via an EPS image and Ghostscript
vLLM 0.32.0 fixes eight CVEs released the same day, including remote code execution via an EPS image and Ghostscript. Analysis and update tips.
NVIDIA DGX Spark 64 GB at $4,999: 100-billion-parameter models on your desk
NVIDIA DGX Spark 64 GB at $4,999: the desktop AI station to run 100-billion-parameter models locally, despite the RAMpocalypse.
Best LM Studio Models (October 2026)
Discover the best LM Studio models in October 2026: up-to-date ranking, Qwen3.6, headless daemon, OpenAI API and local Bionic agent.
Best Ollama Models (October 2026)
Discover the best Ollama models in October 2026: up-to-date ranking of open source models to test locally with version 0.9.x.
**The 2-bit revolution: Ternary-Bonsai-2 and 27B GGUFs run multimodal models on a consumer GPU**
Ternary-Bonsai-2-27B in 2-bit: extreme compression runs 27B multimodal models in GGUF on a consumer GPU. Discover this revolution.
Best Ollama Models (September 2026)
Discover the best Ollama models in September 2026: ranking of powerful local LLMs like Qwen3.6 and Kimi K2.6 combining performance and confidentiality.
Rapid-MLX : the local AI engine 4.2x faster than Ollama on Apple Silicon
Discover Rapid-MLX, the local AI engine 4.2x faster than Ollama on Apple Silicon. Optimize your LLMs and unleash the full power of your Mac.
Best Ollama Models (June 2026)
Discover the June 2026 ranking of the best Ollama models. Benchmark & analysis of local LLMs (Qwen 3.6, DeepSeek V4) for your PC.
Best Lm Studio Models (June 2026)
Discover the best LM Studio models (June 2026) for every setup. Run local open source LLMs easily with no command line.
PewDiePie launches Odysseus: the open source self-hosted AI workspace that challenges ChatGPT and Claude
Discover Odysseus, the open source & self-hosted AI workspace launched by PewDiePie. A project taking on ChatGPT and Claude with 47k GitHub stars.
Ollama 0.30 switches to llama.cpp: the architectural revolution changing local AI
Discover Ollama 0.30: the architectural revolution dropping GGML for llama.cpp. A major update transforming local AI.
OpenAI and Dell push on-premise Codex: the end of cloud-only for enterprise AI
How the OpenAI & Dell deal to deploy Codex on-premise signals the end of all-cloud for enterprise AI.
antirez launches ds4: the local inference engine that makes DeepSeek V4 Flash usable on a Mac
Antirez, Redis creator, launches ds4: a local inference engine making DeepSeek V4 Flash usable on a Mac. Discover this open source project.
How to install a local LLM in 2026
Learn how to set up a local LLM in 2026. Ollama, DeepSeek V4 & Kimi K2.6: simple guide for private, powerful AI with no API fees.
VPS + AI: the complete setup to self-host everything
Build your own AI server on a VPS: choose a host, secure Ubuntu (SSH, UFW, fail2ban), deploy OpenClaw & Caddy. Setup for 5-15€/mo.
APIs AI: OpenRouter vs direct calls
Full OpenRouter vs direct API (OpenAI, Anthropic, Google) comparison. Python code, ModelManager pattern with fallback & rate-limit. Practical guide.
Cloudflare Tunnel: Expose your services without opening ports
Expose services (API, dashboard, webhook) via Cloudflare Tunnel. Zero open ports, auto SSL, free DDoS protection. Step-by-step guide.
Docker + AI: Containerizing Your Intelligent Services
You have a server running an API, a database, a reverse proxy, and maybe a language model. Everything is installed directly on the OS. One day, you update...
Best Local LLMs
Discover the best local LLMs (May 2026). Compare models that protect your data and run on your PC. Click to see the ranking!
Best Lm Studio Models
Discover the best LM Studio models (May 2026) for local, secure, and free AI. Boost your productivity without the cloud!
Best Ollama Models
Discover the best Ollama models (May 2026)! Ranking of top local AIs. No GPU needed, test them quickly on your Mac.
Ollama Vs Lm Studio
Ollama vs LM Studio: which to choose in 2026? Discover our benchmarks, speed gaps, and tips to run your LLM locally.
Vpn For Ai
Access ChatGPT, Claude & Gemini without restrictions! Discover the best VPN for AI and unlock all generative models right now.
AI Hosting
AI Hosting: The 2026 comparison for your projects. Discover the best AWS alternatives to train your models without breaking the bank.