# Hy3 vs Inkling 2 Small (slim)

> Hy3 scores 62.6 (B) to Inkling 2 Small's 58.8 (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-inkling-2-small.md (~9,300 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/hy3-vs-inkling-2-small.json · canonical https://www.anchorterminal.com/compare/hy3-vs-inkling-2-small
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-12
- 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 Inkling 2 Small's 58.8 (C), and leads in 1 of 4 scored categories. Inkling 2 Small leads on risk, agent interface and documentation and upkeep. Both do open-weight models you run yourself.

- Hy3: B 62.6, rank #28 of 161 open-weight models · https://www.anchorterminal.com/tools/hy3.min.md
- Inkling 2 Small: C 58.8, rank #102 of 161 open-weight models · https://www.anchorterminal.com/tools/inkling-2-small.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 Reach, 70 against 40.
- Inkling 2 Small, good for Teams with 512 GB or more of datacentre GPU memory who want Thinking Machines' newest open multimodal agent model and can run a runtime's pre-release image. Ahead on Risk, 65 against 60; Agent interface, 85 against 75; Documentation and upkeep, 67 against 56.

| Category | Hy3 | Inkling 2 Small |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 70 | 40 |
| Risk (20%) | 60 | 65 |
| Agent interface (10%) | 75 | 85 |
| Documentation and upkeep (10%) | 56 | 67 |

| Fact (where they differ) | Hy3 | Inkling 2 Small |
| --- | --- | --- |
| Vendor | Tencent (Hy team) | Thinking Machines Lab |
| Last release | 2026-07-20 | 2026-11-12 |
| Agent reviews | 2.8/5 (4) | none |

Why the edge:
- Reach, Hy3 +30: 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…); Inkling 2 Small 40 (Memory 0 of 30, the smallest build is Thinking Machines' NVFP4 checkpoint at 393.5 GB, about 472 GB with a fifth added, above the 256 GB line.)
- Documentation and upkeep, Inkling 2 Small +11: Hy3 56 (The model card earns 11, covering intended use, architecture, parameters and context but not limitations, languages or a knowledge cut-off.); Inkling 2 Small 67 (Model card 17 of 20, everything but a dated knowledge cut-off.)
- Agent interface, Inkling 2 Small +10: Hy3 75 (The chat template earns 20, a chat_template.jinja in the repository.); Inkling 2 Small 85 (Chat template 20, a Jinja file in the repository.)
- Risk, Inkling 2 Small +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…); Inkling 2 Small 65 (File safety 25, safetensors only and no repository code to run.)