felineflock
- Karma
- 0
- Created
- ()
- Submissions
- 0
- AI Home Lab for Beginners: The Deep Dive (augmentedmind.substack.com)
-
I have been benchmarking local LLMs on a Mac M4 Pro 24 GB RAM using LM Studio. I've tested mostly with 4-bit quantization, both MLX and GGUF, from 4b to 35b models, with speeds of 3 to 40 tokens/second. Results briefly:…
- Why your local LLM feels dumber than it is (forum.level1techs.com)
- Problematic Paper Screener detects 1000s of fraudulent/slop scientific articles (theconversation.com)
- What Luxury Housing Does to Homelessness [video] (youtube.com)
- What happens when companies replace managers with AI? (analysis.infocentral.net)
- Bonsai: The First Commercially Viable 1-Bit LLM (prismml.com)
- Context Rot: How Increasing Input Tokens Impacts LLM Performance (trychroma.com)
- Wine 11 rewrites how Linux runs Windows games at kernel with massive speed gains (xda-developers.com)
- Who Tried to Put Age Verification into Linux (and Why?) (sambent.com)
- HP trialed mandatory 15-minute support call wait times (2025) (arstechnica.com)
- Minoxidil toxicosis in cats and dogs: A scoping review and call to action (sciencedirect.com)
- 1190: Time (prize-winning Xkcd comic animation) (deplicator.github.io)