Mmamonuinmamonu.hashnode.dev·6h ago · 12 min readTurning a Dell OptiPlex 7060 SFF into a Cheap Local AI Inference BoxThere is something appealing about running local AI on hardware that looks as if it should still be opening Excel spreadsheets in an accounting department. My machine is a Dell OptiPlex 7060 SFF. It i10
Mmamonuinmamonu.hashnode.dev·15h ago · 10 min readRunning a A 27B Model in 3.5 GB VRAMBonsai-27B-gguf is Qwen3.6-27B with every weight stored as a single bit. The file is 3.5 GB and it fits on an 8 GB GPU. FP16 weights for a 27B model are about 54 GB. A conventional 4-bit GGUF is about00
Mmamonuinmamonu.hashnode.dev·17h ago · 12 min readExposing an LM Studio Server Running in WSL2 to Your LANFirstly lets get LM Studio running from within the WSL2 (which stands for Windows Subsystem for Linux) ! Running the LM Studio GUI inside WSL2 One slightly unusual part of my setup is that I am not ru00
