Beyond the models getting better; there are still huge gains available in the inference engine side with new tricks like Dflash, MRT, turboquant - for some usecases these can multiply the speeds. There are even some model specific optimized kernels like for DeepSeek 4 flash that seem wild.
Makes me feel we are nowhere near the optimum yet.
With MDM solutions you can not only get software update management, but even full LOM for models that support this.
There are free and open source MDM out there.