Janus bundles llama.cpp Vulkan DLLs into a 50MB Go binary for cross-vendor GGUF local LLM inference across AMD, Intel, and Nvidia GPUs without Python or Docker.
Local LLMs & Homelabs
14 Articles in this Category
Running open-weights without cloud APIs: VRAM sizing, Ollama, vLLM, GGUF/EXL2 quantization, and Apple Silicon unified memory.
Backblaze reports 1.73% annualized failures for Q2 2026. Drive-days, fleet age and sample size explain why that figure is not a home-NAS forecast.
China Telecom’s Xing4.0-29B-A4B activates about 4 billion parameters for each token, but it stores 29 billion parameters…
OrcaSAQ-2 shrinks a 27B coding model to about 12GB. We examine its fidelity results, agent benchmarks, and the practical limits of running it on a 16GB GPU.
Cyber-Prime 1.1 is a specialized 2.6-billion-parameter language model developed by security researcher Akahsizrr. Built directly on Liquid…
Apple’s M5 Ultra Mac Studio introduces a quad-die silicon packaging topology delivering 1.2 TB/s of unified memory…
Google Antigravity SDK now runs local models offline. Use this interactive CLI trick to run Ollama, LM Studio, or Gemma 4 LiteRT on your local machine.
Break free from cloud filters. Discover the 5 best uncensored AI image models to run locally in 2026—from FLUX.1 to Qwen 2.1 and Chroma. Full VRAM benchmarks.
Needle 3 delivers 86% tool accuracy in an 8MB–29MB binary at 4,000 tok/sec. Cactus Compute’s laddered architecture replaces generative chat with edge automation.
ConvAI Innovations’ 0.4B non-autoregressive decision model Laya hit #1 trending on Hugging Face in 48 hours, matching Jev’s sub-35ms speed under Apache 2.0.