128 GB of memory is nice, but you can get started with local agentic AI workflows with much less. By connecting gemma 4 in @lmstudio to MATLAB MCP Server, you can run a local AI model that uses MATLAB as a tool on a 16 GB RAM MacBook Pro. 🔗 spr.ly/6010BD2aXC

@MATLAB @lmstudio what quant are you running gemma 4 at to fit on 16gb

@MATLAB @lmstudio

@MATLAB @lmstudio 16GB 能跑起来这点还挺实用的

@MATLAB @lmstudio yeah and the reason 16GB clears is the model isn't holding the compute, MATLAB is. gemma just needs context headroom. with good quant you could probably push that floor way lower.

@MATLAB @lmstudio I tried one on my macbook air with 16gb, it was rough