Dropping Cloudflare for Bunny.net(jola.dev)

355 points by shintoist 6 months ago | 184 comments

A blog post describing the author's motivation and experience moving their Elixir/Phoenix blog from Cloudflare to bunny.net.

Building a Blog with Elixir and Phoenix(jola.dev)

72 points by shintoist 7 months ago | 5 comments

Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code(ai.georgeliu.com)

380 points by vbtechguy 6 months ago | 94 comments

A blog post walking through setting up Google Gemma 4 26B for local inference on macOS using LM Studio 0.4.0's headless lms CLI, and using it with Claude Code.

Running local models is good now(vickiboykis.com)

1490 points by jfb 4 months ago | 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.

LLMs are breaking 20 year old system design(zknill.io)

25 points by zknill 5 months ago | 15 comments

How much memory do you need to run 1M concurrent tasks?(pkolaczk.github.io)

197 points by pkolaczk 3 years ago | 168 comments

Running local models is good now(vickiboykis.com)

1490 points by jfb 4 months ago | 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.

Reproducing GPT-2 in llm.c(github.com)

578 points by tosh 2 years ago | 109 comments

A GitHub discussion in Andrej Karpathy's llm.c repository about reproducing GPT-2 training from scratch in C/CUDA.

Experimenting with Local LLMs on macOS(blog.6nok.org)

367 points by frontsideair 1 year ago | 241 comments

A personal blog post by a self-described LLM skeptic explaining how to download and run large language models locally on a Mac.

Quickemu: Quickly run optimised Windows, macOS and Linux virtual machines(github.com)

411 points by overbytecode 2 years ago | 128 comments

GitHub repository for Quickemu, a tool that quickly creates and runs optimised Windows, macOS and Linux desktop virtual machines using QEMU.

Training LLMs from ground zero as a startup(yitay.net)

360 points by swyx 2 years ago | 92 comments

Yi Tay's blog post on the experience of training large language models from scratch at a startup (Reka), covering compute, infrastructure, and lessons learned.

How GLM built its own inference infrastructure(z.ai)

373 points by whiteros_e 1 month ago | 261 comments

Z.ai research blog post describing how its GLM model was used to build its own inference infrastructure, framed as a step toward recursive self-improvement.