Aiza's AI Hardware Co.

← Back to models

What it takes to run GLM-5.2

Z.ai (Zhipu AI) · leaderboard rank #7 · MIT license

Our recommendation

To run GLM-5.2, you'll need at least ~904 GB of GPU memory — here's the minimum real setup that gets you there: 1× NVIDIA DGX B200, totaling $400,000 and drawing 10200 W (about 8.5 average homes' worth of continuous power).

How big is this model?

Parameters are the internal numbers an AI model learned during training — think of them loosely as the model's "brain cells." More parameters usually means a more capable model, but it also means the model needs more GPU memory to run.

GLM-5.2 has about 753 billion total parameters. It's a Mixture-of-Experts model, so only about 39 billion parameters are "active" for any given word it generates. Some large models are "Mixture-of-Experts" models: they have a huge total number of parameters, but only wake up a smaller subset (the "active" parameters) for any single word they generate. The full model still has to sit in GPU memory, but the active count is closer to how much raw computation each step actually takes.

The official Hugging Face model card (huggingface.co/zai-org/GLM-5.2) states "Model size: 753B params." Some secondary sources cite 744B instead — we use the 753B figure stated directly on the model card.

The ~39B active-parameter figure comes from third-party technical write-ups rather than being stated as plainly on the card itself, so treat it as less certain than the 753B total.

The memory math, done in the open

Our rule of thumb: 1 GB of GPU memory for every 1 billion parameters, plus 20% extra working room. AI software needs some extra breathing room beyond the raw size of the model itself — for temporary calculations, for the running conversation, and for multiple requests at once. We add 20% on top of the model's raw size as a safe, standard rule-of-thumb minimum for that breathing room.

753 billion parameters × 1 GB = 753 GB
753 GB × 1.20 (20% working room) = 904 GB minimum GPU memory

This is a floor, not a comfortable production number — it assumes one request at a time and no extra safety margin. Real deployments usually want more.

The minimum real build that fits

NVIDIA DGX B200, an official NVIDIA product photo

1× NVIDIA DGX B200

Combined GPU memory
1440 GB (need 904 GB minimum)
GPU memory (also called VRAM) is the fast memory built into the graphics card itself. The AI model has to fit entirely (or almost entirely) inside this memory to run at a decent speed. This is usually the single most important number when you're buying hardware to run a specific AI model — if the model doesn't fit, it either won't load, or it runs painfully slowly.
Total price
$400,000
This is the price of the hardware itself, in US dollars. It does not include electricity, cooling, networking gear, or setup labor.

What that power draw means

10200 W

Power draw is how much electricity the hardware pulls when it's working hard, measured in watts (W). It affects your electricity bill, and at large scale, whether your building's power and cooling can even support the equipment.

  • 8.5 average homes' worth of continuous power — To make a watt number feel real: we compare it to an average home, which draws roughly 1,200 watts around the clock (lights, fridge, HVAC, electronics, etc., averaged over a day). Dividing hardware wattage by 1,200 tells you how many average homes' worth of continuous power the hardware uses.
  • would drain a typical 90 kWh EV battery in about 8.8 hours — To make power draw feel real over time, we compare it to a typical electric car battery, which holds about 90 kWh (kilowatt-hours) of energy. That tells you roughly how many hours of running the hardware it would take to burn through one full EV battery's worth of energy.

Ready to move forward?

Tell us your name and email and we'll follow up about this exact package — no payment, no account needed.

Other builds that would also fit

Want more headroom for real traffic, not just the bare minimum? Try the startup guide or mid-size company guide.