Runs on a private AI box you own
One compact GB10-class device — 128 GB unified memory — runs it on-premise, sold and provisioned by us. No cloud API keys, no data leaving the building.
Run GLM-4.5-Air on-premises
○ Memory-fit arithmetic — checkable math, not a deployment claim
GLM-4.5-Air is the lighter member of the GLM-4.5 family — 106 billion total parameters with about 12 billion active — released under the permissive MIT license and tuned for agentic and coding work. It fits one GB10-class unit at 4-bit.
Here is the arithmetic on a 128 GB unit.
Memory fit on a 128 GB unit
| Parameters | 106B total, ~12B active per token (MoE) |
|---|---|
| 4-bit weights | ~55 GB |
| Device memory | 128 GB unified (one unit) |
| Left for context cache + system | roughly 55 GB |
| Units required | 1 |
At ~55 GB the model fits one unit with generous context headroom; the full GLM-4.5 (~355B) does not — see the limits.
What it serves well
- Agentic and tool-calling workflows on the box.
- Coding assistance where an MIT license is a clean fit.
- General assistant duty with a permissive, commercial-friendly license.
Honest limits
- Arithmetic, not our measured deployment. The envelope is within what this hardware runs comfortably.
- The full GLM-4.5 / 4.6 (~355B) does NOT fit a single 128 GB unit — this page is specifically about the Air variant.
Frequently asked questions
- Does GLM-4.5-Air fit one unit?
- Yes — ~55 GB at 4-bit against 128 GB leaves roughly 55 GB for context and system.
- License?
- MIT — permissive and commercial-friendly, verified against the model's release.
- Can I run the full GLM-4.5 on one box?
- No — the full 355B model exceeds a single 128 GB unit. The Air variant on this page is the one that fits.