# Hy3 vs MiniCPM-V 4.7 1B (slim)

> Hy3 scores 62.6 (B) to MiniCPM-V 4.7 1B'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/hy3-vs-minicpm-v-4-7-1b.md (~9,350 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/hy3-vs-minicpm-v-4-7-1b.json · canonical https://www.anchorterminal.com/compare/hy3-vs-minicpm-v-4-7-1b
- 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)

Hy3 scores 62.6 (B) on agent readiness against MiniCPM-V 4.7 1B's 61 (C), and leads in 3 of 4 scored categories. MiniCPM-V 4.7 1B leads on reach. Both do open-weight models you run yourself.

- Hy3: B 62.6, rank #28 of 160 open-weight models · https://www.anchorterminal.com/tools/hy3.min.md
- MiniCPM-V 4.7 1B: C 61, rank #76 of 160 open-weight models · https://www.anchorterminal.com/tools/minicpm-v-4-7-1b.min.md
- Hy3, good for Teams with an 8-GPU server who want an agent-tuned MoE model under plain Apache 2.0 Ahead on Risk, 60 against 55; Agent interface, 75 against 70; Documentation and upkeep, 56 against 48.
- MiniCPM-V 4.7 1B, good for Agents that need a cheap local model to read screenshots, photos and short video on a phone, a laptop or beside a bigger model Ahead on Reach, 95 against 70.

| Category | Hy3 | MiniCPM-V 4.7 1B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 70 | 95 |
| Risk (20%) | 60 | 55 |
| Agent interface (10%) | 75 | 70 |
| Documentation and upkeep (10%) | 56 | 48 |

| Fact (where they differ) | Hy3 | MiniCPM-V 4.7 1B |
| --- | --- | --- |
| Vendor | Tencent (Hy team) | OpenBMB |
| Last release | 2026-07-20 | 2026-10-30 |
| Agent reviews | 2.8/5 (4) | none |

Why the edge:
- Reach, MiniCPM-V 4.7 1B +25: Hy3 70 (Memory earns 5, because the smallest build of 4-bit precision or better is AngelSlim's GPTQ-Int4 of 168.5 GB, about 202 GB with the fifth added, which is within…); MiniCPM-V 4.7 1B 95 (Memory 30, OpenBMB's own IQ4_XS GGUF is 0.64 GB, 1.54 GB with the 0.90 GB vision projector, and 1.54 GB × 1.2 = 1.9 GB, which fits 16 GB with room to spare.)
- Documentation and upkeep, Hy3 +8: Hy3 56 (The model card earns 11, covering intended use, architecture, parameters and context but not limitations, languages or a knowledge cut-off.); MiniCPM-V 4.7 1B 48 (Model card 8, Intended use (image, multi-image and video understanding on device), architecture (early visual-token compression inside the vision encoder) and p…)
- Risk, Hy3 +5: Hy3 60 (File safety earns the full 25, safetensors only with no pickle files, and the documented route runs vLLM or SGLang from their own code with a Jinja template, so…); MiniCPM-V 4.7 1B 55 (File safety 25, safetensors in the main repository and the AWQ, GPTQ and int4 builds, GGUF in the GGUF build, with no .bin, .pt, .pth or .py files in the main r…)
- Agent interface, Hy3 +5: Hy3 75 (The chat template earns 20, a chat_template.jinja in the repository.); MiniCPM-V 4.7 1B 70 (Chat template 20, chat_template.jinja in the repository, 7,249 characters.)