# Apertus v1.5 8B vs WeVisOne-VL-4B (slim)

> Apertus v1.5 8B and WeVisOne-VL-4B 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-wevisone-vl-4b.md (~9,550 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-wevisone-vl-4b.json · canonical https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-wevisone-vl-4b
- 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 WeVisOne-VL-4B score within a point of each other on agent readiness, 61 (C) and 61 (C). WeVisOne-VL-4B 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
- WeVisOne-VL-4B: C 61, rank #84 of 160 open-weight models · https://www.anchorterminal.com/tools/wevisone-vl-4b.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 70; Documentation and upkeep, 84 against 48.
- WeVisOne-VL-4B, good for Agents that need to locate, count or cut out objects in images on a small GPU, under a permissive licence Ahead on Reach, 70 against 40.

| Category | Apertus v1.5 8B | WeVisOne-VL-4B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 40 | 70 |
| Risk (20%) | 75 | 55 |
| Agent interface (10%) | 85 | 70 |
| Documentation and upkeep (10%) | 84 | 48 |

| Fact (where they differ) | Apertus v1.5 8B | WeVisOne-VL-4B |
| --- | --- | --- |
| Vendor | Swiss AI Initiative (EPFL and ETH Zurich) | Tencent (WeChat Vision) |
| 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 | 2026-10-27 |
| Agent reviews | 2.8/5 (4) | none |

Why the edge:
- Documentation and upkeep, Apertus v1.5 8B +36: Apertus v1.5 8B 84 (Model card 14 of 20, languages and a knowledge cut-off are missing.); WeVisOne-VL-4B 48 (Model card 8, Intended use, limitations and the architecture are on the card.)
- Reach, WeVisOne-VL-4B +30: 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.); WeVisOne-VL-4B 70 (Memory 30, the only build from Tencent is the BF16 safetensors file with its decoder, 9.7 GB, and 9.7 GB × 1.2 = 11.6 GB, within 16 GB.)
- Risk, Apertus v1.5 8B +20: Apertus v1.5 8B 75 (File safety 25, safetensors only and no code in the repository.); WeVisOne-VL-4B 55 (File safety 15, the backbone is safetensors, but mask_decoder.pt, a PyTorch pickle the card calls a required component, sits beside it.)
- Agent interface, Apertus v1.5 8B +15: Apertus v1.5 8B 85 (Chat template 20, a Jinja file in the repository.); WeVisOne-VL-4B 70 (Chat template 20, chat_template.jinja in the repository (5,292 characters), Qwen3-VL's template.)