# Cola2 vs Ripple-65B Preview (slim)

> Ripple-65B Preview scores 53.3 (D) 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-ripple-65b-preview.md (~8,950 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/cola2-vs-ripple-65b-preview.json · canonical https://www.anchorterminal.com/compare/cola2-vs-ripple-65b-preview
- 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)

Ripple-65B Preview scores 53.3 (D) on agent readiness against Cola2's 33.9 (F), and leads in 3 of 4 scored categories. Cola2 leads on documentation and upkeep. 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
- Ripple-65B Preview: D 53.3, rank #135 of 160 open-weight models · https://www.anchorterminal.com/tools/ripple-65b-preview.min.md
- Cola2, good for Researchers working on latent or diffusion language models who want a checkpoint to study Ahead on Documentation and upkeep, 58 against 49.
- Ripple-65B Preview, good for Teams with Blackwell GPUs or a DGX Spark who want an Apache 2.0 coding model to try for terminal and agentic coding work, and can run the publisher's code to serve it. Ahead on Reach, 45 against 25; Risk, 55 against 40; Agent interface, 75 against 20.

| Category | Cola2 | Ripple-65B Preview |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 25 | 45 |
| Risk (20%) | 40 | 55 |
| Agent interface (10%) | 20 | 75 |
| Documentation and upkeep (10%) | 58 | 49 |

| Fact (where they differ) | Cola2 | Ripple-65B Preview |
| --- | --- | --- |
| Vendor | ByteDance (Seed) | Ricursive Intelligence |
| Licence | None stated for the weights (the code is Apache 2.0) | Apache-2.0 |
| Last release | 2026-11-06 | 2026-11-04 |
| Terms last updated | no document linked | not read yet |

Why the edge:
- Agent interface, Ripple-65B Preview +55: Cola2 20 (Chat template 20, A chat template in tokenizer_config.json (4,116 characters), which came with the Qwen3 tokenizer.); Ripple-65B Preview 75 (Chat template 20, chat_template.jinja in the repository.)
- Reach, Ripple-65B Preview +20: 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.); Ripple-65B Preview 45 (Memory 10 of 30, the smallest 4-bit build is Ricursive's NVFP4 at 57.2 GB, 68.7 GB with a fifth added, which is over 64 GB and fits our reference machine.)
- Risk, Ripple-65B Preview +15: Cola2 40 (File safety 15, safetensors only, no .bin, .pt or .pth files (25).); Ripple-65B Preview 55 (File safety 15, safetensors only, less 10 because the documented way to run it loads Ricursive's Python.)
- Documentation and upkeep, Cola2 +9: 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…); Ripple-65B Preview 49 (Model card 14 of 20, no limitations and no knowledge cut-off.)