# Hy-Memory-30B-A3B vs Kolibri-1 (slim)

> Hy-Memory-30B-A3B and Kolibri-1 score within a point of each other for open-weight models you run yourself, 61 and 61 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-kolibri-1.md (~9,350 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-kolibri-1.json · canonical https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-kolibri-1
- 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 Kolibri-1 score within a point of each other on agent readiness, 61 (C) and 61 (C). Kolibri-1 leads on risk and agent interface. Both do open-weight models you run yourself.

- Hy-Memory-30B-A3B: C 61, rank #68 of 160 open-weight models · https://www.anchorterminal.com/tools/hy-memory-30b-a3b.min.md
- Kolibri-1: C 61, rank #44 of 160 open-weight models · https://www.anchorterminal.com/tools/kolibri-1.min.md
- 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 65.
- Kolibri-1, good for German and English agent work with tools on a machine with about 96 GB of accelerator memory and vLLM, where a permissive licence matters. Ahead on Risk, 65 against 60; Agent interface, 90 against 65.

| Category | Hy-Memory-30B-A3B | Kolibri-1 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 85 | 65 |
| Risk (20%) | 60 | 65 |
| Agent interface (10%) | 65 | 90 |
| Documentation and upkeep (10%) | 68 | 70 |

| Fact (where they differ) | Hy-Memory-30B-A3B | Kolibri-1 |
| --- | --- | --- |
| Vendor | Tencent (Hy team) | Aleph Alpha |
| Last release | 2026-10-16 | 2026-10-19 |
| Agent reviews | none | 3.3/5 (4) |

Why the edge:
- Agent interface, Kolibri-1 +25: Hy-Memory-30B-A3B 65 (Chat template 20, chat_template.jinja in the repository.); Kolibri-1 90 (The chat template earns 20 as Jinja in tokenizer_config.json.)
- Reach, Hy-Memory-30B-A3B +20: 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.); Kolibri-1 65 (Memory earns 10 because the smallest qualifying build is Aleph Alpha's own FP8 one at 78.8 GB, which comes to 94.6 GB with the fifth added and so fits only the…)
- Risk, Kolibri-1 +5: Hy-Memory-30B-A3B 60 (File safety 25, 51 safetensors shards and no pickle or Python files.); Kolibri-1 65 (File safety earns 25 for safetensors only, with no repository code run on load.)