Hacker News new | ask | show | jobs
by kethinov 19 days ago
It's not speedy. I get 1-3 tokens per second.

The machine:

CPU: 24 × AMD Ryzen 9 9900X 12-Core Processor

RAM: 128gb

GPU: NVIDIA GeForce RTX 4060 Ti 16gb (I typo'd the GPU above)

(This is via Ollama on Ubuntu.)

But 1-3 tokens per second is much faster than a lot of other high end models I've tried, so I was pretty pleased with it. Obviously other models run much faster on this hardware though.