Run GLM-4.5-Air locally: hardware requirements
GLM-4.5-Air needs about 219 GB of GPU memory for one person at 32K context, and about 11.5 GB more for each extra person at 64K. For 80 users working as AI agents, plan on 397 GB, which takes 3 × H200 NVL.
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-4.5-Air
On Hugging FaceZ.ai, China · 110B parameters · License: mit
What you need for 16 active users
3 × H200 NVL
It holds the model and up to 16 active users at 64K context.
The server
1 TB RAM
32 CPU cores
1 TB NVMe
Rules of thumb
- GPU memory in total
- 397 GB
- Weights
- 221 GB (published files)
- Conversation cache, all active
- 184 GB
- Engine (vLLM)
- 3.0 GB
Ways to need less
- Use 32K context per person2 × B200
- Use 8K context per person2 × H200 NVL
- Use a 4-bit build2 × H200 NVL
- 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. 11 cards too small for this model are left out.
| Card | Memory | Active users, one server | For your 16 active |
|---|---|---|---|
| A100 | 80 GB | 21 | 6 × A100 |
| B200 | 180 GB | 26 | 3 × B200 |
| H100 | 80 GB | 21 | 6 × H100 |
| H200 NVL | 141 GB | 16 | 3 × H200 NVL |
| L40S | 48 GB | 9 | 2 servers, each with 7 × L40S |
| RTX PRO 6000 Blackwell | 96 GB | 21 | 5 × 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-4.5-Air 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 | 259 GB | 2 × H200 NVL |
| 80 | 16 | 397 GB | 3 × H200 NVL |
| 120 | 24 | 489 GB | 3 × B200 |
| 500 | 100 | 1363 GB | 8 × B200 |
Similar models
- GLM-5.3-FlashZ.ai · 321B · 1035 GB for 16 at once
- GLM-4.7-FlashZ.ai · 31B · 437 GB for 16 at once
- GLM-5.3Z.ai · 753B · 4465 GB for 16 at once
- GLM-5Z.ai · 754B · 2684 GB for 16 at once
- gpt-oss-120bOpenAI · 117B · 137 GB for 16 at once
- NVIDIA-Nemotron-3-Super-120B-A12B-BF16NVIDIA · 124B · 326 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-4.5-Air need?
GLM-4.5-Air needs about 219 GB of GPU memory for one person at 32K context, and about 11.5 GB more for each extra person at 64K. For 80 users working as AI agents, plan on 397 GB, which takes 3 × H200 NVL.
How many active users can GLM-4.5-Air handle on one 96 GB GPU?
GLM-4.5-Air 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-4.5-Air run on a 24 GB GPU such as the RTX 4090?
Not as published for one person at 32K context: it needs about 219 GB. A 4-bit or 8-bit build may fit, if the model has one.
What license does GLM-4.5-Air 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