# Hy-Memory-30B-A3B vs WeVisOne-VL-4B (slim)

> Hy-Memory-30B-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/hy-memory-30b-a3b-vs-wevisone-vl-4b.md (~9,800 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-wevisone-vl-4b.json · canonical https://www.anchorterminal.com/compare/hy-memory-30b-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)

Hy-Memory-30B-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 agent interface. Both do open-weight models you run yourself.

- Hy-Memory-30B-A3B: C 61, rank #68 of 160 open-weight models · https://www.anchorterminal.com/tools/hy-memory-30b-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
- 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 70; Risk, 60 against 55; Documentation and upkeep, 68 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 Agent interface, 70 against 65.

| Category | Hy-Memory-30B-A3B | WeVisOne-VL-4B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 85 | 70 |
| Risk (20%) | 60 | 55 |
| Agent interface (10%) | 65 | 70 |
| Documentation and upkeep (10%) | 68 | 48 |

| Fact (where they differ) | Hy-Memory-30B-A3B | WeVisOne-VL-4B |
| --- | --- | --- |
| Vendor | Tencent (Hy team) | Tencent (WeChat Vision) |
| Last release | 2026-10-16 | 2026-10-27 |
| Terms last updated | no document linked | not read yet |

Why the edge:
- Documentation and upkeep, Hy-Memory-30B-A3B +20: 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)…); WeVisOne-VL-4B 48 (Model card 8, Intended use, limitations and the architecture are on the card.)
- Reach, Hy-Memory-30B-A3B +15: 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.); 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, Hy-Memory-30B-A3B +5: Hy-Memory-30B-A3B 60 (File safety 25, 51 safetensors shards and no pickle or Python files.); 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, WeVisOne-VL-4B +5: Hy-Memory-30B-A3B 65 (Chat template 20, chat_template.jinja in the repository.); WeVisOne-VL-4B 70 (Chat template 20, chat_template.jinja in the repository (5,292 characters), Qwen3-VL's template.)