Run GLM-5 locally: hardware requirements
GLM-5 needs about 1475 GB of GPU memory for one person at 32K context, and about 78.0 GB more for each extra person at 64K. For 80 users working as AI agents, plan on 2684 GB, which takes A cluster of about 16 × B200 across 2 servers.
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-5
On Hugging FaceZ.ai, China · 754B parameters · License: mit
What you need for 16 active users
A cluster of about 16 × B200 across 2 servers
The model is too large for one 8-card server, so its copy has to span servers. That needs an engine and network built for it.
The server
4 TB RAM
32 CPU cores
4 TB NVMe
Rules of thumb
- GPU memory in total
- 2684 GB
- Weights
- 1508 GB (published files)
- Conversation cache, all active
- 1248 GB
- Engine (vLLM)
- 3.0 GB
Ways to need less
- Use 32K context per personA cluster of about 13 × B200 across 2 servers
- Use 8K context per personA cluster of about 10 × B200 across 2 servers
- Use a 4-bit build2 servers, each with 7 × B200
- Use a smaller model: gpt-oss-120b1 × B200
- Use a smaller model: Mixtral-8x7B-Instruct-v0.11 × B200
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. 17 cards too small for this model are left out.
No card on our list holds this model in one server.
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-5 by team size
AI agents, 1 user in 5 active at a time, 64K context, as published.
| Total users | At once | GPU memory | What you need |
|---|---|---|---|
| 20 | 4 | 1748 GB | A cluster of about 11 × B200 across 2 servers |
| 80 | 16 | 2684 GB | A cluster of about 16 × B200 across 2 servers |
| 120 | 24 | 3308 GB | A cluster of about 20 × B200 across 3 servers |
| 500 | 100 | 9236 GB | A cluster of about 55 × B200 across 7 servers |
Similar models
- GLM-5.3Z.ai · 753B · 4465 GB for 16 at once
- GLM-5.3-FlashZ.ai · 321B · 1035 GB for 16 at once
- GLM-4.5-AirZ.ai · 110B · 397 GB for 16 at once
- GLM-4.7-FlashZ.ai · 31B · 437 GB for 16 at once
- DeepSeek-V4.1-FlashDeepSeek · 763B · 568 GB for 16 at once
- DeepSeek-V4.1-Flash-1017DeepSeek · 763B · 568 GB for 16 at once
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-5 need?
GLM-5 needs about 1475 GB of GPU memory for one person at 32K context, and about 78.0 GB more for each extra person at 64K. For 80 users working as AI agents, plan on 2684 GB, which takes A cluster of about 16 × B200 across 2 servers.
How many active users can GLM-5 handle on one 96 GB GPU?
GLM-5 does not fit on one 96 GB card such as the RTX PRO 6000 Blackwell at 64K context. Compare larger cards or a smaller precision above.
Can GLM-5 run on a 24 GB GPU such as the RTX 4090?
Not as published for one person at 32K context: it needs about 1475 GB. A 4-bit or 8-bit build may fit, if the model has one.
What license does GLM-5 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