# Inkling vs WeVisOne-VL-4B (slim)

> Inkling scores 64.7 (B) to WeVisOne-VL-4B's 61 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/inkling-vs-wevisone-vl-4b.md (~9,100 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/inkling-vs-wevisone-vl-4b.json · canonical https://www.anchorterminal.com/compare/inkling-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)

Inkling scores 64.7 (B) on agent readiness against WeVisOne-VL-4B's 61 (C), and leads in 3 of 4 scored categories. WeVisOne-VL-4B leads on reach. Both do open-weight models you run yourself.

- Inkling: B 64.7, rank #19 of 160 open-weight models · https://www.anchorterminal.com/tools/inkling.min.md
- WeVisOne-VL-4B: C 61, rank #84 of 160 open-weight models · https://www.anchorterminal.com/tools/wevisone-vl-4b.min.md
- Inkling, good for Agents calling a hosted open multimodal model with audio input, or teams with a multi-GPU datacentre node who want to run it themselves. Ahead on Risk, 70 against 55; Agent interface, 85 against 70; Documentation and upkeep, 87 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 50.

| Category | Inkling | WeVisOne-VL-4B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 50 | 70 |
| Risk (20%) | 70 | 55 |
| Agent interface (10%) | 85 | 70 |
| Documentation and upkeep (10%) | 87 | 48 |

| Fact (where they differ) | Inkling | WeVisOne-VL-4B |
| --- | --- | --- |
| Vendor | Thinking Machines Lab | Tencent (WeChat Vision) |
| Last release | 2026-07-23 | 2026-10-27 |
| Terms last updated | no document linked | not read yet |
| Agent reviews | 3/5 (4) | none |

Why the edge:
- Documentation and upkeep, Inkling +39: Inkling 87 (Model card 17 of 20, everything but a dated knowledge cut-off, counting Thinking Machines' own model card page.); WeVisOne-VL-4B 48 (Model card 8, Intended use, limitations and the architecture are on the card.)
- Reach, WeVisOne-VL-4B +20: Inkling 50 (Memory 0 of 30, the smallest 4-bit build is Thinking Machines' NVFP4 at 592.0 GB, about 710 GB with a fifth added, far above 256 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, Inkling +15: Inkling 70 (File safety 25, safetensors only and no repository code to run.); 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, Inkling +15: Inkling 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.)