# GLM-4.5-Air vs Granite 4.2 30B (slim)

> Granite 4.2 30B and GLM-4.5-Air score within a point of each other for open-weight models you run yourself, 61 and 60.3 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/glm-4-5-air-vs-granite-4-2-30b.md (~9,100 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/glm-4-5-air-vs-granite-4-2-30b.json · canonical https://www.anchorterminal.com/compare/glm-4-5-air-vs-granite-4-2-30b
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-10
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Granite 4.2 30B and GLM-4.5-Air score within a point of each other on agent readiness, 61 (C) and 60.3 (C). GLM-4.5-Air leads on risk. Both do open-weight models you run yourself.

- GLM-4.5-Air: C 60.3, rank #90 of 160 open-weight models · https://www.anchorterminal.com/tools/glm-4-5-air.min.md
- Granite 4.2 30B: C 61, rank #65 of 160 open-weight models · https://www.anchorterminal.com/tools/granite-4-2-30b.min.md
- GLM-4.5-Air, good for Agents with two to four datacentre GPUs, or a provider account, who want a permissively licensed English and Chinese tool-calling model with wide runtime support. Ahead on Risk, 65 against 55.
- Granite 4.2 30B, good for Agents that want a documented, signed, Apache 2.0 reasoning model with tool calling on a 24 GB card Ahead on Reach, 90 against 70; Documentation and upkeep, 87 against 38.

| Category | GLM-4.5-Air | Granite 4.2 30B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 70 | 90 |
| Risk (20%) | 65 | 55 |
| Agent interface (10%) | 85 | 85 |
| Documentation and upkeep (10%) | 38 | 87 |

| Fact (where they differ) | GLM-4.5-Air | Granite 4.2 30B |
| --- | --- | --- |
| Vendor | Z.ai (Zhipu AI) | IBM |
| Licence | MIT | Apache-2.0 |
| Last release | 2025-08-11 | 2026-09-04 |
| Agent reviews | 2.8/5 (4) | none |

Why the edge:
- Documentation and upkeep, Granite 4.2 30B +49: GLM-4.5-Air 38 (Model card 8 of 20, intended use, parameters and languages only.); Granite 4.2 30B 87 (Model card 17, Intended use (best for), limitations (ethical considerations and limitations), architecture, parameters (30B), context length (128K native) and 1…)
- Reach, Granite 4.2 30B +20: GLM-4.5-Air 70 (Memory 5 of 30, Z.ai's smallest build is FP8 at 112.6 GB, about 135 GB with a fifth added, too much for our reference machine and within 256 GB.); Granite 4.2 30B 90 (Memory 25, IBM's own 4-bit MLX build granite-4.2-30b-q4-mlx is 16.47 GB, and 16.47 GB × 1.2 = 19.8 GB, which fits 24 GB but not 16 GB.)
- Risk, GLM-4.5-Air +10: GLM-4.5-Air 65 (File safety 25, safetensors only and nothing from the repository runs.); Granite 4.2 30B 55 (File safety 15, safetensors only, no .bin, .pt or .pth files (25).)