# Ornith-1.5-35B-A3B vs WeVisOne-VL-4B (slim)

> Ornith-1.5-35B-A3B 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/ornith-1-5-35b-a3b-vs-wevisone-vl-4b.md (~9,850 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/ornith-1-5-35b-a3b-vs-wevisone-vl-4b.json · canonical https://www.anchorterminal.com/compare/ornith-1-5-35b-a3b-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)

Ornith-1.5-35B-A3B and WeVisOne-VL-4B score within a point of each other on agent readiness, 61 (C) and 61 (C). WeVisOne-VL-4B leads on risk and documentation and upkeep. Both do open-weight models you run yourself.

- Ornith-1.5-35B-A3B: C 61, rank #50 of 160 open-weight models · https://www.anchorterminal.com/tools/ornith-1-5-35b-a3b.min.md
- WeVisOne-VL-4B: C 61, rank #84 of 160 open-weight models · https://www.anchorterminal.com/tools/wevisone-vl-4b.min.md
- Ornith-1.5-35B-A3B, good for Local coding and terminal agents on a 24 to 32 GB GPU or a Mac, where a clear licence file and an answering publisher aren't required Ahead on Reach, 90 against 70; Agent interface, 85 against 70.
- 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 Risk, 55 against 50; Documentation and upkeep, 48 against 36.

| Category | Ornith-1.5-35B-A3B | WeVisOne-VL-4B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 70 |
| Risk (20%) | 50 | 55 |
| Agent interface (10%) | 85 | 70 |
| Documentation and upkeep (10%) | 36 | 48 |

| Fact (where they differ) | Ornith-1.5-35B-A3B | WeVisOne-VL-4B |
| --- | --- | --- |
| Vendor | Ornith | Tencent (WeChat Vision) |
| Licence | MIT | Apache-2.0 |
| Last release | 2026-08-23 | 2026-10-27 |
| Terms last updated | no document linked | not read yet |
| Agent reviews | 2.3/5 (4) | none |

Why the edge:
- Reach, Ornith-1.5-35B-A3B +20: Ornith-1.5-35B-A3B 90 (Memory 25, since Ornith's own MLX 4-bit build is 19.5 GB and needs about 23.4 GB with the fifth added, which fits 24 GB, while its Q4_K_M GGUF, NVFP4 build and…); 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.)
- Agent interface, Ornith-1.5-35B-A3B +15: Ornith-1.5-35B-A3B 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.)
- Documentation and upkeep, WeVisOne-VL-4B +12: Ornith-1.5-35B-A3B 36 (Model card 11, it covers intended use, architecture, parameters and context but not limitations, languages or a knowledge cut-off.); WeVisOne-VL-4B 48 (Model card 8, Intended use, limitations and the architecture are on the card.)
- Risk, WeVisOne-VL-4B +5: Ornith-1.5-35B-A3B 50 (File safety 25, safetensors and GGUF only and no Python in any of Ornith's repositories for this size, so the card's --trust-remote-code flag loads nothing from…); 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.)