QDNASales and integration of LLM inference and training platforms, on-premises or hybrid

Running Qwen 3.6 27B on GB300 NVL72

Qwen 3.6 27B has 27 billion parameters. GB300 NVL72 offers 20,700 GB of HBM3e across a 72-GPU rack memory. This page puts the two side by side.

Short answer. Qwen 3.6 27B fits comfortably on GB300 NVL72. In FP16, its weights take about 62.1 GB of the 20,700 GB available, leaving 20,638 GB for the attention cache and concurrency.

How much memory does Qwen 3.6 27B need?

Weights take the parameter count multiplied by the format size, plus a 15% runtime margin for activations and buffers. The attention cache sits on top: it grows with context length and with the number of concurrent requests, so it is sized case by case.

FormatWeights in memory On this machineWhat the format costs
FP1662.1 GBfitsfull precision, the quality reference
FP831.0 GBfitsnegligible loss on most tasks
NVFP415.5 GBfitsBlackwell format, native FP4 compute
Q415.5 GBfitsblock quantisation, broadly supported

What is left to serve requests?

Qwen 3.6 27B fits comfortably on GB300 NVL72. In FP16, its weights take about 62.1 GB of the 20,700 GB available, leaving 20,638 GB for the attention cache and concurrency. The remaining margin decides how many concurrent requests and how much context the machine sustains. A margin below a quarter of memory forces a limit on context or on concurrency.

GB300 NVL72 ranges from from 3,9 M€, indicative and not contractual. The machine targets the GE segment.

Where else can Qwen 3.6 27B run?

See the Qwen 3.6 27B and GB300 NVL72 fact sheets.

How much memory does Qwen 3.6 27B need?

In FP16, weights take about 62.1 GB including the runtime margin. The attention cache sits on top and depends on context.

Does Qwen 3.6 27B fit on GB300 NVL72?

Qwen 3.6 27B fits comfortably on GB300 NVL72. In FP16, its weights take about 62.1 GB of the 20,700 GB available, leaving 20,638 GB for the attention cache and concurrency.

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.