AI · Official
Serving GLM-5.3 Across Two NVIDIA DGX Stations With vLLM When One GPU Falls Short
NVIDIA Technical blog ·

At a glance
The GLM-5.3 NVFP4 model is too large for a single GPU to hold. This guide shows how to link two NVIDIA DGX Stations and serve the model through one address using vLLM.
Key points
- The model has 753 billion parameters and needs about 464GB of memory.
- One GPU has 252GB of memory, so the model is split across two.
- Both stations compute every request and return answers through one OpenAI-compatible address.
- At 16 concurrent requests throughput peaked at 607.8 tokens per second, then fell to 385.0 at 32.
Why it matters
It shows what hardware setup and performance limits apply when individuals or small teams run a large AI model themselves.
Original source
When One GPU Isn’t Enough: Serving GLM-5.3 Across Two NVIDIA DGX Stations with vLLM
NVIDIA Technical blog · Nov 14, 02:00 KST
Read on NVIDIA Technical blog ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to NVIDIA Technical blog.
More from this field
- Google Drops Search Button and Adds AI Sidebar to Its Search Homepage
Google has officially rolled out a redesigned desktop search homepage after a successful test. The Google Search button next to the search bar is gone, and a row of AI buttons now sits under the bar. Logged-in users also get a sidebar showing their recent AI Mode conversations.
Ars Technica · Nov 21, 06:58 KST - Meta Rethinks 2030 Net-Zero Goal as AI Data Center Emissions Hit Record High
Meta's 2026 sustainability report said the company is re-evaluating its 2030 net-zero goal. Its emissions rose about 40 percent from 2024 to 2025, the largest jump among the big US tech companies.
Ars Technica · Nov 21, 06:47 KST - Anthropic Mathematician Says Claude Helped Crack the Riemann Hypothesis
Levent Alpöge, a mathematician at Anthropic, says he has proved the Riemann hypothesis with help from Claude, Anthropic's AI system. Instead of a regular math paper, he posted a four-page note and linked to computer code that he says checks the result. The claim still needs to be verified.
The New York Times · Nov 21, 06:47 KST - Designers Say Ssense's Website Shows Their Clothes Inaccurately
Designer Reese Cooper noticed his RCOS puffer coat looked distorted on the luxury retailer Ssense's website, with a chest hook drawn far too large. Ssense said some site images came from a "virtual try-on" program, though it would not say whether that program uses AI.
The New York Times · Nov 21, 06:16 KST