Serving Qwen 3.6 27B with Triton Inference Server
Qwen 3.6 27B has 27 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?
Qwen 3.6 27B totals 27 billion parameters. In NVFP4 its weights take about 15.5 GB including the runtime margin. In FP8 the footprint doubles, to about 31.0 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 Qwen 3.6 27B fact sheets.
On which platforms?
- Qwen 3.6 27B on DGX Spark
- Qwen 3.6 27B on Mac Studio Ultra
- Qwen 3.6 27B on DGX Station
- Qwen 3.6 27B on RTX PRO 6000 server
- Qwen 3.6 27B on H200 SXM server
- Qwen 3.6 27B on B200 SXM
How much memory for Qwen 3.6 27B with Triton Inference Server?
About 15.5 GB in NVFP4 for the weights, excluding the attention cache.
Does Triton Inference Server suit Qwen 3.6 27B?
Triton Inference Server serves Qwen 3.6 27B as soon as the machine offers at least 15.5 GB of memory, the weight footprint in NVFP4. 8 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.