# Arete-27B vs Ripple-65B Preview (slim)

> Arete-27B scores 55.1 (C) to Ripple-65B Preview's 53.3 (D) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/arete-27b-vs-ripple-65b-preview.md (~8,750 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/arete-27b-vs-ripple-65b-preview.json · canonical https://www.anchorterminal.com/compare/arete-27b-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)

Arete-27B scores 55.1 (C) on agent readiness against Ripple-65B Preview's 53.3 (D), and leads in 2 of 4 scored categories. Ripple-65B Preview leads on agent interface. Both do open-weight models you run yourself.

- Arete-27B: C 55.1, rank #123 of 160 open-weight models · https://www.anchorterminal.com/tools/arete-27b.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
- Arete-27B, good for Agents that want Qwen3.8-27B's coding and tool use without its handling of politically sensitive topics, on a 24 GB card or a 128 GB machine Ahead on Reach, 50 against 45; Documentation and upkeep, 63 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 Agent interface, 75 against 60.

| Category | Arete-27B | Ripple-65B Preview |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 50 | 45 |
| Risk (20%) | 55 | 55 |
| Agent interface (10%) | 60 | 75 |
| Documentation and upkeep (10%) | 63 | 49 |

| Fact (where they differ) | Arete-27B | Ripple-65B Preview |
| --- | --- | --- |
| Vendor | Nous Research | Ricursive Intelligence |
| 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 +15: Arete-27B 60 (Chat template 20, a Jinja file in the repository.); Ripple-65B Preview 75 (Chat template 20, chat_template.jinja in the repository.)
- Documentation and upkeep, Arete-27B +14: Arete-27B 63 (Model card 8, no limitations, context length, languages or cut-off.); Ripple-65B Preview 49 (Model card 14 of 20, no limitations and no knowledge cut-off.)
- Reach, Arete-27B +5: Arete-27B 50 (Memory 10, the only build from Nous Research is the 54.7 GB BF16 release, which needs about 66 GB and fits the reference machine.); 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.)