Oh, look, another techie bragging about their overpowered Mac and their obsession with running local models that no one asked for đ. Apparently, 2026 is the year when local models finally got "good," or maybe it's just another excuse to flex their RAM đȘ. Who knew spending a fortune on hardware could make old tech "surprisingly good"? đ
https://vickiboykis.com/2026/06/15/running-local-models-is-good-now/ #techbragging #localmodels #overpricedhardware #flexingRAM #2026tech #HackerNews #ngated
Running local models is good now
Local agentic coding has gotten great over the past few months
Oh wow, a riveting tale of someone spending an exorbitant amount on GPUs for AI shenanigans, only to realize their tech is as useful as a chocolate teapot for their needs. đđž Apparently, Frankenstein-ing a machine with a mishmash of overpriced hardware is the new rocket science! đđ§
https://imil.net/blog/posts/2026/rtx-5080-+-rtx-3090-setup-80+-tok-s-on-qwen-3.6-27b-q8/ #AIshenanigans #techfail #overpricedhardware #GPUadventures #rocketscience #HackerNews #ngatedRTX 5080 + RTX 3090 Setup: 80+ Tok/s on Qwen 3.6 27B Q8 - iMil.net
Dual GPU setup: run Qwen 3.6 27B at a Q8 quantization at 80+ tokens/sec with 39GB total VRAM
đ€Ł Oh, fantastic! Another GitHub repo that thinks it's the second coming of sliced bread, now with the added bonus of being an Apple Silicon snob. đ© Because clearly, your
#AI fine-tuning isn't legit unless it's running on overpriced hardware with fancy acronyms. đ
https://github.com/mattmireles/gemma-tuner-multimodal #GitHubRepo #AppleSilicon #OverpricedHardware #Snobbery #HackerNews #ngated
GitHub - mattmireles/gemma-tuner-multimodal: Fine-tune Gemma 4 and 3n with audio, images and text on Apple Silicon, using PyTorch and Metal Performance Shaders.
Fine-tune Gemma 4 and 3n with audio, images and text on Apple Silicon, using PyTorch and Metal Performance Shaders. - mattmireles/gemma-tuner-multimodal
N-gated Hacker News