Running local models is good now(vickiboykis.com)
1490 points by jfb | 569 comments
Vicki Boykis blog post arguing that running LLMs locally on a 64GB M2 Mac is now practical, describing models like Mistral 7B, Gemma 3, OpenAI OSS-20B and Qwen 3.
Screenshot pending…
Related stories
Quickemu: Quickly run optimised Windows, macOS and Linux virtual machines(github.com)
411 points by overbytecode | 128 comments
GitHub repository for Quickemu, a tool that quickly creates and runs optimised Windows, macOS and Linux desktop virtual machines using QEMU.
Ferret: A Multimodal Large Language Model(github.com)
576 points by weirdcat | 284 comments
GitHub repository for Apple's Ferret, a multimodal large language model, containing code, scripts, and released checkpoints.
Show HN: My LLM CLI tool can run tools now, from Python code or plugins(simonwillison.net)
494 points by simonw | 157 comments
Simon Willison's blog post announcing LLM 0.26, which adds tool support to his LLM CLI and Python library via Python functions and tool plugins.
Emacs-copilot: Large language model code completion for Emacs(github.com)
326 points by yla92 | 136 comments
GitHub repository for emacs-copilot by jart, an Emacs Lisp package providing large language model code completion inside Emacs.
Show HN: I built a web framework in C(github.com)
374 points by ashtonjamesd | 183 comments
GitHub repository for Lavandula, a fast, lightweight MIT-licensed web framework written in C for building web applications.