turbo-fieldfare
Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac
Open-source projects. Clever little tools. Big ideas.
Unearthed from the Hacker News community.
Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac
Clawk – Give coding agents a disposable Linux VM, not your laptop
qm
GigaToken: ~1000x faster Language model tokenization
Formally verified 3D CSG: Trust 93 lines spec, not 1000 lines AI code
Ctrlb-decompose: Strip the noise from logs before sending to LLMs
Uv 0.12.0
OpenAI Forked Git on GitHub
Jamesob's guide to running SOTA LLMs locally
Cuts Long Horizon Inference Costs by 50% via external KV Cache Offload
I was tired of opening 2 tabs for every HN link, so I made a userscript
FableCut – A browser video editor AI agents can drive (zero deps)
Distill and serve small models with frontier quality for half the cost
I put a $2.43 necklace on 3 outfits. VLMs priced it at $19 to $104
Train and run transformers directly on Apple's Neural Engine
Claude is just Mr. Meeseeks
Command and Conquer Generals natively ported to macOS, iPhone, iPad using Fable
Offline tool to stabilize TV volume using IR control and spike detection