Local AI
How to run open-weight AI models on your own hardware: what each model needs, and the machines that reach it.
-
12 Sep 2026
DeepSeek V4.1-Flash needs 510GB, and nothing can run it yet
Flash names a fast model, not a small one. The compression has already been spent and no released engine loads the architecture. Here is what it will need, and the DeepSeek you can run today.
-
12 Sep 2026
GLM-5.3 hardware requirements
744B weights, 40B active per token, and a 4-bit build that wants 475GB. What the strongest open model needs, what you give up at each quantisation, and which machines reach it.
-
12 Sep 2026
How much memory to run an open model locally
Total parameters set the memory bill. Active parameters set the speed. A capacity ladder for the open models of 2026, from 17GB to 1.6TB.
