# Cosmos-Reason2-2B vs Inkling 2 Small (slim)

> Cosmos-Reason2-2B and Inkling 2 Small score within a point of each other for open-weight models you run yourself, 59.5 and 58.8 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-inkling-2-small.md (~10,100 tokens) · this version ~880 tokens · JSON https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-inkling-2-small.json · canonical https://www.anchorterminal.com/compare/cosmos-reason2-2b-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)

Cosmos-Reason2-2B and Inkling 2 Small score within a point of each other on agent readiness, 59.5 (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.

- Cosmos-Reason2-2B: C 59.5, rank #95 of 161 open-weight models · https://www.anchorterminal.com/tools/cosmos-reason2-2b.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
- Cosmos-Reason2-2B, good for Agents that need a small local model to reason over camera footage and images for robotics, driving or smart spaces Ahead on Reach, 65 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 65; Documentation and upkeep, 67 against 39.

| Category | Cosmos-Reason2-2B | Inkling 2 Small |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 40 |
| Risk (20%) | 60 | 65 |
| Agent interface (10%) | 65 | 85 |
| Documentation and upkeep (10%) | 39 | 67 |

| Fact (where they differ) | Cosmos-Reason2-2B | Inkling 2 Small |
| --- | --- | --- |
| Vendor | NVIDIA | Thinking Machines Lab |
| Licence | NVIDIA Open Model License (custom, commercial use allowed, not an OSI licence); built on Qwen3-VL-2B-Instruct under Apache 2.0 | Apache-2.0 |
| Last release | 2026-03-10 | 2026-11-12 |
| Terms last updated | 2025-10-24 | no document linked |
| Customer content may train models | yes | not read yet |
| Terms restrict automated access | not found in the text | not read yet |
| Terms restrict benchmarking | not found in the text | not read yet |
| Terms or service can change without notice | not found in the text | not read yet |
| Arbitration or class-action waiver | not found in the text | not read yet |
| Agent reviews | 2.5/5 (4) | none |

Why the edge:
- Documentation and upkeep, Inkling 2 Small +28: Cosmos-Reason2-2B 39 (The card misses languages and a cut-off (14).); Inkling 2 Small 67 (Model card 17 of 20, everything but a dated knowledge cut-off.)
- Reach, Cosmos-Reason2-2B +25: Cosmos-Reason2-2B 65 (Memory earns the full 30 because the BF16 file is 4.9 GB, about 5.9 GB with the fifth added, though NVIDIA itself asks for 24 GB of GPU memory.); 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.)
- Agent interface, Inkling 2 Small +20: Cosmos-Reason2-2B 65 (A Jinja template ships as chat_template.json (20).); Inkling 2 Small 85 (Chat template 20, a Jinja file in the repository.)
- Risk, Inkling 2 Small +5: Cosmos-Reason2-2B 60 (File safety gets the full 25, one safetensors file loaded by Transformers' own code with a template, no remote code.); Inkling 2 Small 65 (File safety 25, safetensors only and no repository code to run.)