GeForce GTX 485M 

I wonder what this means for the Tesla line, and whether we will see a variant of Maxwell with a large boost in 64-bit performance, or if that line will be in an awkward place until Pascal.

The memory, but not the cache, is capable of ECC (error-correction) for enterprises who do not want a stray photon to mess up their computation.

Considering the GTX 965M has 1024 CUDA cores many felt it would use GM206 as well, but that didn’t happen; in a similar fashion, those expecting (hoping) GTX 960M and 950M would use a derivative of GM206 are also going to be disappointed and it continues to use the GM107 chip.

Interestingly, the clocks and core configurations mean that potentially the GTX 950M is actually a bit slower than GTX 850M (640 cores at 936MHz + Boost compared to 914MHz + Boost), but NVIDIA doesn't disclose the full range of base clocks and Boost clocks so the 950M will hit higher clocks on average compared to 850M.

Although not inexpensive, it will allow customers to get some extra mileage out of their laptop, especially with the major improvements in performance we have seen with the Maxwell 2 based GTX 980M and GTX 970M.

This will let owners of older laptops, who are not interested in a complete upgrade, obtain the power of the new Maxwell 2 based GPUs from NVIDIA in their laptop.

Despite their same name, mobile GPUs are always way below their desktop counterparts for obvious reasons, and while that might happened before, the new Maxwell 2.0 changes everything and closes the relative performance gap placing the performance of the mobile GTX 980M at around 80 percent of the GTX 980.

Efficiency is quite impressive considering the GPU is still based on the 28nm manufacturing process.