Serving Kimi K3 with Triton Inference Server
Kimi K3 has 2800 billion parameters. Triton Inference Server targets industrial deployment across several models. This page gives the memory required and the platforms that qualify.
What is the minimum memory?
Kimi K3 totals 2800 billion parameters. In NVFP4 its weights take about 1,610 GB including the runtime margin. In FP8 the footprint doubles, to about 3,220 GB. The attention cache sits on top and depends on the context served.
What is Triton Inference Server for?
Triton Inference Server targets industrial deployment across several models. See the Triton Inference Server and Kimi K3 fact sheets.
On which platforms?
How much memory for Kimi K3 with Triton Inference Server?
About 1,610 GB in NVFP4 for the weights, excluding the attention cache.
Does Triton Inference Server suit Kimi K3?
Triton Inference Server serves Kimi K3 as soon as the machine offers at least 1,610 GB of memory, the weight footprint in NVFP4. 2 of the 8 platforms in the catalogue meet that bar.
Method
Parameter counts and memory figures come from the site fact sheets. Memory footprints are calculated, not measured: a reading on real hardware may differ depending on the engine and the exact weight format. Prices are indicative and not contractual.