# Apertus v1.5 8B vs Hy-Memory-30B-A3B (slim)

> Apertus v1.5 8B and Hy-Memory-30B-A3B 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/apertus-v1-5-8b-vs-hy-memory-30b-a3b.md (~9,850 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-hy-memory-30b-a3b.json · canonical https://www.anchorterminal.com/compare/apertus-v1-5-8b-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)

Apertus v1.5 8B and Hy-Memory-30B-A3B score within a point of each other on agent readiness, 61 (C) and 61 (C). Hy-Memory-30B-A3B leads on reach. Both do open-weight models you run yourself.

- Apertus v1.5 8B: C 61, rank #40 of 160 open-weight models · https://www.anchorterminal.com/tools/apertus-v1-5-8b.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
- Apertus v1.5 8B, good for Agents that want a fully open, multilingual 8B with image and audio input on one 24 GB GPU, and can run a publisher fork of vLLM. Ahead on Risk, 75 against 60; Agent interface, 85 against 65; Documentation and upkeep, 84 against 68.
- 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 40.

| Category | Apertus v1.5 8B | Hy-Memory-30B-A3B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 40 | 85 |
| Risk (20%) | 75 | 60 |
| Agent interface (10%) | 85 | 65 |
| Documentation and upkeep (10%) | 84 | 68 |

| Fact (where they differ) | Apertus v1.5 8B | Hy-Memory-30B-A3B |
| --- | --- | --- |
| Vendor | Swiss AI Initiative (EPFL and ETH Zurich) | Tencent (Hy team) |
| Licence | Apache-2.0, with the Apertus Acceptable Use Policy (v1.5, 14 July 2026) accepted at the download gate | Apache-2.0 |
| Last release | 2026-10-14 | 2026-10-16 |
| Terms last updated | not read yet | no document linked |
| Agent reviews | 2.8/5 (4) | none |

Why the edge:
- Reach, Hy-Memory-30B-A3B +45: Apertus v1.5 8B 40 (Memory 25 of 30, the BF16 files are 18.4 GB, or 22.1 GB with a fifth added, which fits 24 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.)
- Agent interface, Apertus v1.5 8B +20: Apertus v1.5 8B 85 (Chat template 20, a Jinja file in the repository.); Hy-Memory-30B-A3B 65 (Chat template 20, chat_template.jinja in the repository.)
- Documentation and upkeep, Apertus v1.5 8B +16: Apertus v1.5 8B 84 (Model card 14 of 20, languages and a knowledge cut-off are missing.); 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)…)
- Risk, Apertus v1.5 8B +15: Apertus v1.5 8B 75 (File safety 25, safetensors only and no code in the repository.); Hy-Memory-30B-A3B 60 (File safety 25, 51 safetensors shards and no pickle or Python files.)