# Cola2 vs Inkling-Small (slim)

> Inkling-Small scores 67 (B) to Cola2's 33.9 (F) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/cola2-vs-inkling-small.md (~8,850 tokens) · this version ~680 tokens · JSON https://www.anchorterminal.com/compare/cola2-vs-inkling-small.json · canonical https://www.anchorterminal.com/compare/cola2-vs-inkling-small
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-10
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Inkling-Small scores 67 (B) on agent readiness against Cola2's 33.9 (F), and leads in every scored category. Both do open-weight models you run yourself.

- Cola2: F 33.9, rank #160 of 160 open-weight models · https://www.anchorterminal.com/tools/cola2.min.md
- Inkling-Small: B 67, rank #13 of 160 open-weight models · https://www.anchorterminal.com/tools/inkling-small.min.md
- Cola2, good for Researchers working on latent or diffusion language models who want a checkpoint to study
- Inkling-Small, good for Teams with 256 GB or more of datacentre GPU memory who want an open multimodal agent model with audio input and adjustable thinking. Ahead on Reach, 55 against 25; Risk, 70 against 40; Agent interface, 85 against 20; Documentation and upkeep, 87 against 58.

| Category | Cola2 | Inkling-Small |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 25 | 55 |
| Risk (20%) | 40 | 70 |
| Agent interface (10%) | 20 | 85 |
| Documentation and upkeep (10%) | 58 | 87 |

| Fact (where they differ) | Cola2 | Inkling-Small |
| --- | --- | --- |
| Vendor | ByteDance (Seed) | Thinking Machines Lab |
| Licence | None stated for the weights (the code is Apache 2.0) | Apache-2.0 |
| Last release | 2026-11-06 | 2026-07-31 |
| Agent reviews | none | 3.5/5 (4) |

Why the edge:
- Agent interface, Inkling-Small +65: Cola2 20 (Chat template 20, A chat template in tokenizer_config.json (4,116 characters), which came with the Qwen3 tokenizer.); Inkling-Small 85 (Chat template 20, a Jinja file in the repository.)
- Reach, Inkling-Small +30: Cola2 25 (Memory 15, the only build is the F32 safetensors set, 35.07 GB, and 35.07 GB × 1.2 = 42.1 GB, within 64 GB.); Inkling-Small 55 (Memory 5 of 30, the smallest 4-bit build is Thinking Machines' NVFP4 at 170.8 GB, about 205 GB with a fifth added, so it needs 256 GB.)
- Risk, Inkling-Small +30: Cola2 40 (File safety 15, safetensors only, no .bin, .pt or .pth files (25).); Inkling-Small 70 (File safety 25, safetensors only and no repository code to run.)
- Documentation and upkeep, Inkling-Small +29: Cola2 58 (Model card 8, Intended use and limitations (the out-of-scope list, and the unconverged latent model) and the architecture are on the card and the GitHub model c…); Inkling-Small 87 (Model card 17 of 20, everything but a dated knowledge cut-off, counting Thinking Machines' own model card page.)