Even in chinese trained models too. the amount of tokens it requires to communicate the same ideas is higher. it is just less efficient to tokenize the Chinese language because logographic languages are archaic, ridiculous, and inefficient compared to latin languages.
M5 Ultra will ship before end of year, likely. Though with current RAM shortage, likely max spec will be 256GB and in short supply.
In late 2027 or early 2028, Nvidia will release Vera Rubin DGX Spark, likely with double or better the performance of current Blackwell, though unclear if memory capacity will go up much from current 128GB. Two to four of those will run models like this decently.
In 2028 we should expect Vera Rubin RTX discrete lineup, including the replacement to the RTX PRO 6000. Likely memory spec will be minimum 128GB. Good chance of up to 200GB. Two to four of those will run NVFP4 models in this class very well.
It might be M6 Ultra and I think the real reason for stopping selling top-tier units was to avoid mid-generation price hikes and increasing demand for the more expensive next-gen systems that I assume will come with 512gb (maybe 1TB) of RAM and a massive markup to match.
I feel like the models are good enough for a decade of future work. So Once you have a working set up you can keep using it to do the work at the same level. There will be better stuff and may make that type of work obsolete but if you can do useful things it won’t be worth less.
I think there is a gap right now for running large models such as GLM 5.2 in Q4 or Q8.
My hope is on Intel Crescent Island 480GB cards. Let‘s see how expensive they‘ll be.
Officially, they are allowed if they consist of interpreted code and don't significantly change the functionality of the app as reviewed. Unofficially, they probably don't have a robust enforcement mechanism.
It’s really a pity, why can’t they feel superior while breaking ToS and copyrights just like Americans can feel superior over Deepseek while breaking ToS and copyrights?
