# Apertus v1.5 8B vs Qwen-AgentWorld-35B-A3B (slim)

> Apertus v1.5 8B scores 61 (C) to Qwen-AgentWorld-35B-A3B's 52.1 (D) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-qwen-agentworld-35b-a3b.md (~10,200 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-qwen-agentworld-35b-a3b.json · canonical https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-qwen-agentworld-35b-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 scores 61 (C) on agent readiness against Qwen-AgentWorld-35B-A3B's 52.1 (D), and leads in 3 of 4 scored categories. Qwen-AgentWorld-35B-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
- Qwen-AgentWorld-35B-A3B: D 52.1, rank #141 of 160 open-weight models · https://www.anchorterminal.com/tools/qwen-agentworld-35b-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 55; Agent interface, 85 against 50; Documentation and upkeep, 84 against 41.
- Qwen-AgentWorld-35B-A3B, good for Agent builders who want to train or test an agent against simulated tools, terminals, browsers and phones on a 128 GB machine Ahead on Reach, 55 against 40.

| Category | Apertus v1.5 8B | Qwen-AgentWorld-35B-A3B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 40 | 55 |
| Risk (20%) | 75 | 55 |
| Agent interface (10%) | 85 | 50 |
| Documentation and upkeep (10%) | 84 | 41 |

| Fact (where they differ) | Apertus v1.5 8B | Qwen-AgentWorld-35B-A3B |
| --- | --- | --- |
| Vendor | Swiss AI Initiative (EPFL and ETH Zurich) | Alibaba (Qwen 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 | 2026-06-25 |
| Terms last updated | not read yet | no document linked |
| Agent reviews | 2.8/5 (4) | none |

Why the edge:
- Documentation and upkeep, Apertus v1.5 8B +43: Apertus v1.5 8B 84 (Model card 14 of 20, languages and a knowledge cut-off are missing.); Qwen-AgentWorld-35B-A3B 41 (Model card 11, the card gives intended use (simulating agent environments), architecture, parameters and context length.)
- Agent interface, Apertus v1.5 8B +35: Apertus v1.5 8B 85 (Chat template 20, a Jinja file in the repository.); Qwen-AgentWorld-35B-A3B 50 (Chat template 20, chat_template.jinja in the repository, the same as the template in tokenizer_config.json.)
- Risk, Apertus v1.5 8B +20: Apertus v1.5 8B 75 (File safety 25, safetensors only and no code in the repository.); Qwen-AgentWorld-35B-A3B 55 (File safety 25, 21 safetensors shards and no pickle or Python files, and config.json has no auto_map.)
- Reach, Qwen-AgentWorld-35B-A3B +15: 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.); Qwen-AgentWorld-35B-A3B 55 (Memory 10, Alibaba's only build is the BF16 safetensors, 69.32 GB, and 69.32 GB × 1.2 = 83.2 GB, above 64 GB and inside the reference machine's GPU share.)