A new inference engine to run Kimi K3 2.78T parameter with 29GB of RAM
marcobambini.substack.com
A new inference engine to run Kimi K3 2.78T parameter with 29GB of RAM
1–3 of 3 posts
Re: A new inference engine to run Kimi K3 2.78T parameter with 29GB of RAM
#2Current speed is “approximately one third of a token per second”
Re: A new inference engine to run Kimi K3 2.78T parameter with 29GB of RAM
#3Current speed is “approximately one third of a token per second”
Right, we trade speed for the ability to run a 2.7T-parameter model while preserving accuracy. It is a first version, and we plan to improve the inference performance.