Use Cases
Industry & Science
Strategy & Intelligence
Resources
Company
Solutions
Staff Software Engineer at OpenTeams. Dask maintainer.
2 articles
MiniCPM5-2B quantization report: the best GGUF weights and K/V cache quants on llama.cpp and BeeLlama.cpp, squeezing a SOTA model into 3 GiB RAM.
LLM intelligence vs cost: logarithmic scales in plots hide the cost chasm between frontier and cheap models; actual OpenRouter prices alter the Pareto frontier.
