What Fits and What Worksgpt-oss-20b is my current go-to locally hosted LLM. I explain why14 min read·mamonu.hashnode.devSep 12
Trusting Local LLMs with Code: Building little-llms-benchAnother LLM Benchmark? In this economy ?9 min read·mamonu.hashnode.devSep 10
Running Large MoE LLMs on Modest Hardware with FreeTokenA new open-source inference engine designed to run MoE models on hardware that doesn't have enough VRAM to hold them15 min read·mamonu.hashnode.devSep 10
Using a mac mini (2012) for LLM inference with KoboldCpp or... "necessity is the mother of invention"24 min read·mamonu.hashnode.dev1YSep 9
