# When One GPU Isn't Enough: Serving GLM-5.3 Across Two NVIDIA DGX Stations

> Two NVIDIA DGX Stations split a 753-billion-parameter AI model across GPUs using tensor parallelism.
- Title: When One GPU Isn't Enough: Serving GLM-5.3 Across Two NVIDIA…
- Summary: Two NVIDIA DGX Stations split a 753-billion-parameter AI model across GPUs using tensor parallelism.
- Keywords: nvidia, dgx, vllm, glm-5.3, tensor parallelism, ai model, gpu memory, distributed computing, ai benchmarking, local ai, NVIDIA Technical Blog
- Source: NVIDIA Technical Blog — https://developer.nvidia.com/blog/when-one-gpu-isnt-enough-serving-glm-5-3-across-two-nvidia-dgx-stations-with-vllm
- Published: 2026-11-13T17:00:00+00:00
- Read time: 1 min
- Topics: nvidia, dgx, vllm, glm-5.3, tensor parallelism, ai model, gpu memory, distributed computing, ai benchmarking, local ai, technology, startups
## Model Memory Challenge
GLM-5.3 NVFP4 requires 464 GB GPU memory exceeding single GB300 GPU's 252 GB HBM3e.
## Two Stations Serve One Model
Two NVIDIA DGX Stations connected via ConnectX-8 RDMA use tensor parallelism to split model weights.
## vLLM Distributed Service
vLLM launches distributed service across both Stations enabling multi-token prediction and FP8 KV-cache storage.
## AIPerf Benchmark Results
Peak throughput at 607.8 tokens per second with concurrency 16, falling to 385.0 tokens per second at concurrency 32.
## Tensor Parallelism Setup
Station A hosts API while Station B runs worker with no API server using tensor parallelism (TP=2).
## Model Checkpoint Validation
Both Stations verify identical checkpoint files with MIXED_PRECISION quantization.
## Service Launch Process
vLLM service starts with multi-token prediction and FP8 KV-cache storage enabled.
## GPU Memory Usage
Each GPU holds 231.35 GB of model weights with 218 GiB per GPU after loading.
## Chat Request Test
Model responds with trend summary and 50% percentage change from Q1 to Q2 units sold.
## Concurrency Testing
AIPerf measures throughput at 607.8 tokens per second with concurrency 16 and 385.0 tokens per second at concurrency 32.
## Resource Cleanup
vLLM container stops after benchmarking with no memory usage remaining.
## Next Steps
Follow Connect Two DGX Stations playbook to link hardware and validate before deployment.
## Real-World Application
Model enables local inference on sensitive data without per-token costs.
## Performance Metrics
Mean request latency 453.5 seconds at concurrency 32 with 385.0 tokens per second throughput.
## GPU Memory Check
nvidia-smi shows VLLM::Worker_TP0 on Station A and VLLM::Worker_TP1 on Station B.
## Model Validation
Both Stations confirm identical checkpoint files with MIXED_PRECISION quantization.
## Key takeaway

NVIDIA DGX Stations serve GLM-5.3 NVFP4 model with 464 GB memory via tensor parallelism at 607.8 tokens per second.