# GLM-4.5-Air vs Inkling 2 Mini (slim)

> Inkling 2 Mini 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-inkling-2-mini.md (~9,150 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/glm-4-5-air-vs-inkling-2-mini.json · canonical https://www.anchorterminal.com/compare/glm-4-5-air-vs-inkling-2-mini
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-20
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Inkling 2 Mini 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 reach. Both do open-weight models you run yourself.

- GLM-4.5-Air: C 60.3, rank #91 of 162 open-weight models · https://www.anchorterminal.com/tools/glm-4-5-air.min.md
- Inkling 2 Mini: C 61, rank #69 of 162 open-weight models · https://www.anchorterminal.com/tools/inkling-2-mini.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 Reach, 70 against 60.
- Inkling 2 Mini, good for Developers with a 32 GB laptop or a single GPU who want a small open agent model with images in and a 1M context, and can run a runtime's pre-release build. Ahead on Risk, 70 against 65; Documentation and upkeep, 57 against 38.

| Category | GLM-4.5-Air | Inkling 2 Mini |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 70 | 60 |
| Risk (20%) | 65 | 70 |
| Agent interface (10%) | 85 | 85 |
| Documentation and upkeep (10%) | 38 | 57 |

| Fact (where they differ) | GLM-4.5-Air | Inkling 2 Mini |
| --- | --- | --- |
| Vendor | Z.ai (Zhipu AI) | Thinking Machines Lab |
| Licence | MIT | Apache-2.0 |
| Last release | 2025-08-11 | 2026-11-20 |
| Agent reviews | 2.8/5 (4) | none |

Why the edge:
- Documentation and upkeep, Inkling 2 Mini +19: GLM-4.5-Air 38 (Model card 8 of 20, intended use, parameters and languages only.); Inkling 2 Mini 57 (Model card 17, no knowledge cut-off.)
- Reach, GLM-4.5-Air +10: 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.); Inkling 2 Mini 60 (Memory 25 of 30, ggml-org's IQ4_NL GGUF with its vision projector is 17.98 GB, about 21.6 GB with a fifth added.)
- Risk, Inkling 2 Mini +5: GLM-4.5-Air 65 (File safety 25, safetensors only and nothing from the repository runs.); Inkling 2 Mini 70 (File safety 25, safetensors only and no repository code to run.)
