News for hackers. Stuff that matters.
Re:Ollama is now available on Windows in preview by jart on Saturday February 17, 2024 @04:15PM (#39413621)
Zen4 AVX512 must be really good then.
Re:Ollama is now available on Windows in preview by imtringued on Sunday February 18, 2024 @05:38AM (#39417963)
To be fair a lot of the GPU edge comes from fast memory. A GPU with 20tflops running a 30 billion parameter model has a compute budget of 700flops per parameter. Meanwhile the sheer size of the model prevents you from loading it more than 20 times from memory per second.