# GLM-4.5-Air vs Hy-Memory-30B-A3B (slim)

> Hy-Memory-30B-A3B 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-hy-memory-30b-a3b.md (~9,600 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/glm-4-5-air-vs-hy-memory-30b-a3b.json · canonical https://www.anchorterminal.com/compare/glm-4-5-air-vs-hy-memory-30b-a3b
- 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)

Hy-Memory-30B-A3B 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 and agent interface. 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
- Hy-Memory-30B-A3B: C 61, rank #68 of 160 open-weight models · https://www.anchorterminal.com/tools/hy-memory-30b-a3b.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 60; Agent interface, 85 against 65.
- Hy-Memory-30B-A3B, good for Agents with an external memory framework that want a local model for the write path on a 24 GB card Ahead on Reach, 85 against 70; Documentation and upkeep, 68 against 38.

| Category | GLM-4.5-Air | Hy-Memory-30B-A3B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 70 | 85 |
| Risk (20%) | 65 | 60 |
| Agent interface (10%) | 85 | 65 |
| Documentation and upkeep (10%) | 38 | 68 |

| Fact (where they differ) | GLM-4.5-Air | Hy-Memory-30B-A3B |
| --- | --- | --- |
| Vendor | Z.ai (Zhipu AI) | Tencent (Hy team) |
| Licence | MIT | Apache-2.0 |
| Last release | 2025-08-11 | 2026-10-16 |
| Agent reviews | 2.8/5 (4) | none |

Why the edge:
- Documentation and upkeep, Hy-Memory-30B-A3B +30: GLM-4.5-Air 38 (Model card 8 of 20, intended use, parameters and languages only.); Hy-Memory-30B-A3B 68 (Model card 8, Intended use (the write path of Mem0, MemOS and Hy-Memory), parameters (30B, about 3B active) and languages (English and Chinese, in the metadata)…)
- Agent interface, GLM-4.5-Air +20: GLM-4.5-Air 85 (Chat template 20, a Jinja file in the repository.); Hy-Memory-30B-A3B 65 (Chat template 20, chat_template.jinja in the repository.)
- Reach, Hy-Memory-30B-A3B +15: 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.); Hy-Memory-30B-A3B 85 (Memory 25, Tencent's own Q4_K_M GGUF is 18.24 GB, and 18.24 GB × 1.2 = 21.9 GB, which fits 24 GB but not 16 GB.)
- Risk, GLM-4.5-Air +5: GLM-4.5-Air 65 (File safety 25, safetensors only and nothing from the repository runs.); Hy-Memory-30B-A3B 60 (File safety 25, 51 safetensors shards and no pickle or Python files.)