GPU VRAM calculator

Run GLM-4.7-Flash locally: hardware requirements

GLM-4.7-Flash needs about 74.0 GB of GPU memory for one person at 32K context, and about 23.5 GB more for each extra person at 64K. For 80 users working as AI agents, plan on 437 GB, which takes 3 × B200.

Z.ai, China. From its files on Hugging Face, checked 2026-11-05.

Context per person: more context lets the model work with longer conversations and more files, and needs more GPU memory for every person. As a guide: 8K for short chat, 32K for chat over documents, 64K for AI agents, whose instructions, tools and files all count.

80 users means about 16 people working at the same moment. That share is a planning assumption; if you know yours, choose the total that matches it.

Work it out for your team: zai-org/GLM-4.7-Flash

On Hugging Face

Z.ai, China · 31B parameters · License: mit

What you need for 16 active users

3 × B200

It holds the model and up to 19 active users at 64K context.

The server

1 TB RAM
48 CPU cores
500 GB NVMe

Rules of thumb

GPU memory in total
437 GB
Weights
62.4 GB (published files)
Conversation cache, all active
375 GB
Engine (vLLM)
3.0 GB

Ways to need less

Your options by card

80 users means about 16 using the model at any moment. The others are not waiting; they are simply doing something else. If more become active than a build handles, they queue. 6 cards too small for this model are left out.

CardMemoryActive users, one serverFor your 16 active
A10080 GB166 × A100
B200180 GB193 × B200
H10080 GB166 × H100
H200 NVL141 GB204 × H200 NVL
L40S48 GB92 servers, each with 6 × L40S
RTX 6000 Ada48 GB54 servers, each with 4 × RTX 6000 Ada
RTX A500024 GB116 servers, each with 4 × RTX A5000
RTX PRO 4000 Blackwell24 GB116 servers, each with 4 × RTX PRO 4000 Blackwell
RTX PRO 4500 Blackwell32 GB28 servers, each with 4 × RTX PRO 4500 Blackwell
RTX PRO 5000 Blackwell48 GB54 servers, each with 4 × RTX PRO 5000 Blackwell
RTX PRO 6000 Blackwell96 GB165 × RTX PRO 6000 Blackwell

These are memory limits. A card can hold more people than it can answer quickly, so test your own workload before you buy. More than one card in a server needs an engine that splits the model.

GLM-4.7-Flash by team size

AI agents, 1 user in 5 active at a time, 64K context, as published.

Total usersAt onceGPU memoryWhat you need
204156 GB1 × B200
8016437 GB3 × B200
12024625 GB4 × B200
5001002466 GB2 servers, each with 8 × B200

All models

How this is worked out

GPU memory = weights + a conversation cache for each person + the serving engine, from this model's files on Hugging Face. These are memory limits, not speed. The full method and its limits.

Questions

How much GPU memory does GLM-4.7-Flash need?

GLM-4.7-Flash needs about 74.0 GB of GPU memory for one person at 32K context, and about 23.5 GB more for each extra person at 64K. For 80 users working as AI agents, plan on 437 GB, which takes 3 × B200.

How many active users can GLM-4.7-Flash handle on one 96 GB GPU?

By memory, about 1 active user at once at 64K context on a card such as the RTX PRO 6000 Blackwell. Speed can set a lower limit, so load-test before you buy.

Can GLM-4.7-Flash run on a 24 GB GPU such as the RTX 4090?

Not as published for one person at 32K context: it needs about 74.0 GB. A 4-bit or 8-bit build may fit, if the model has one.

What license does GLM-4.7-Flash use?

Hugging Face lists its license as mit. Check the license on the model's page before you use it.

Running a model on your own servers?

NeueCode is private autonomous intelligence for enterprise: it takes on your organization's tasks on your own GPUs, with nothing leaving your network, a person approving every action, and all of it on record. It runs each model on one card, so read the single-card figures above.

What you need to run NeueCode