Hacker News new | ask | show | jobs
by bradfa 24 days ago
Many newer Chinese lab models are releasing with int4 native weights. Latest NVIDIA generation GPUs have a hard time with this and can actually be slower than previous generations. This may make Blackwell depreciate faster than other recent generations.
1 comments

That's not a real problem, hardly any 3rd party was running native weights anyways so they'll get quantized to NVFP4