# Inkling 2 Small vs MiniMax-M2.5 (slim)

> MiniMax-M2.5 and Inkling 2 Small score within a point of each other for open-weight models you run yourself, 59 and 58.8 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-m2-5.md (~9,900 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-m2-5.json · canonical https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-m2-5
- 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)

MiniMax-M2.5 and Inkling 2 Small score within a point of each other on agent readiness, 59 (C) and 58.8 (C). Inkling 2 Small leads on risk, agent interface and documentation and upkeep. Both do open-weight models you run yourself.

- Inkling 2 Small: C 58.8, rank #102 of 161 open-weight models · https://www.anchorterminal.com/tools/inkling-2-small.min.md
- MiniMax-M2.5: C 59, rank #99 of 161 open-weight models · https://www.anchorterminal.com/tools/minimax-m2-5.min.md
- 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 30; Agent interface, 85 against 75; Documentation and upkeep, 67 against 37.
- MiniMax-M2.5, good for Teams with a 4 to 8 GPU server who want an open agent and coding model with parallel tool calls and can live with its use policy Ahead on Reach, 65 against 40.

| Category | Inkling 2 Small | MiniMax-M2.5 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 40 | 65 |
| Risk (20%) | 65 | 30 |
| Agent interface (10%) | 85 | 75 |
| Documentation and upkeep (10%) | 67 | 37 |

| Fact (where they differ) | Inkling 2 Small | MiniMax-M2.5 |
| --- | --- | --- |
| Vendor | Thinking Machines Lab | MiniMax |
| Licence | Apache-2.0 | MiniMax Model License (model) and modified MIT (code) |
| Last release | 2026-11-12 | 2026-02-12 |
| Agent reviews | none | 1.8/5 (4) |

Why the edge:
- Risk, Inkling 2 Small +35: Inkling 2 Small 65 (File safety 25, safetensors only and no repository code to run.); MiniMax-M2.5 30 (File safety earns 15, safetensors only with no pickle files, less 10 because every documented loading route passes trust_remote_code for the repository's Python…)
- Documentation and upkeep, Inkling 2 Small +30: Inkling 2 Small 67 (Model card 17 of 20, everything but a dated knowledge cut-off.); MiniMax-M2.5 37 (The model card earns 2, stating only intended use and leaving out limitations, architecture, parameters, context, natural languages and a cut-off.)
- Reach, MiniMax-M2.5 +25: 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.); MiniMax-M2.5 65 (Memory earns 5. MiniMax only publishes its 230 GB FP8 release, and the smallest build of 4-bit or better from a runtime's own library is LM Studio's MLX 4-bit a…)
- Agent interface, Inkling 2 Small +10: Inkling 2 Small 85 (Chat template 20, a Jinja file in the repository.); MiniMax-M2.5 75 (The chat template earns 20 for chat_template.jinja in the repository.)