# Olmo 3 7B Think vs Ripple-65B Preview (slim)

> Ripple-65B Preview scores 53.3 (D) to Olmo 3 7B Think's 52.3 (D) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/olmo-3-7b-think-vs-ripple-65b-preview.md (~7,800 tokens) · this version ~1,480 tokens · JSON https://www.anchorterminal.com/compare/olmo-3-7b-think-vs-ripple-65b-preview.json · canonical https://www.anchorterminal.com/compare/olmo-3-7b-think-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: 2026-11-04
- 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 Olmo 3 7B Think's 52.3 (D), and leads in 1 of 4 scored categories. Olmo 3 7B Think leads on reach and risk. Both do open-weight models you run yourself.

- Olmo 3 7B Think: D 52.3, rank #107 of 121 open-weight models · https://www.anchorterminal.com/tools/olmo-3-7b-think.min.md
- Ripple-65B Preview: D 53.3, rank #103 of 121 open-weight models · https://www.anchorterminal.com/tools/ripple-65b-preview.min.md
- Olmo 3 7B Think, good for Researchers and agents that want a small fully open reasoning model for maths and code, with its training data on hand Ahead on Reach, 75 against 45; Risk, 75 against 55.
- 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 35.

| Category | Olmo 3 7B Think | Ripple-65B Preview |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 75 | 45 |
| Risk (20%) | 75 | 55 |
| Agent interface (10%) | 35 | 75 |
| Documentation and upkeep (10%) | 52 | 49 |

| Fact (where they differ) | Olmo 3 7B Think | Ripple-65B Preview |
| --- | --- | --- |
| Vendor | Ai2 (Allen Institute for AI) | Ricursive Intelligence |
| Licence | Apache-2.0, with Ai2's Responsible Use Guidelines named on the card | Apache-2.0 |
| Last release | 2026-06-25 | 2026-11-04 |
| Terms last updated | 2024-09-25 | not read yet |
| Privacy policy last updated | 2025-02-19 | 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 | yes | not read yet |
| Arbitration or class-action waiver | not found in the text | not read yet |
| Agent reviews | 2.8/5 (4) | none |

Why the edge:
- Agent interface, Ripple-65B Preview +40: Olmo 3 7B Think 35 (The chat template earns 20 for chat_template.jinja in the repository. The tool-calling format earns 10, since only the template and vLLM's own parser describe it. Trained tool calling earns nothing, because Ai2's report says tool calling was trained into the Instruct model, not Think. Structured output earns nothing. Reasoning control earns nothing, since it always thinks. Context earns 5 for 65,536 tokens trained. 20 + 10 + 0 + 0 + 0 + 5 = 35.); Ripple-65B Preview 75 (Chat template 20, chat_template.jinja in the repository. Tool-calling format 25, Ricursive's server README says how tools are declared and calls come back, with the ripple parser in SGLang 0.5.19. Trained tool calling 20, one or more calls a turn and agentic-coding RL. Structured output 0, not documented. Reasoning control 0, the template has no thinking switch or effort levels. Context 10, long-context training at 2M-token sequences for a stated 1M.)
- Reach, Olmo 3 7B Think +30: Olmo 3 7B Think 75 (Memory earns the full 30, since Ollama's 4-bit build is 4.5 GB and fits 8 GB (per the 21 October check of Ollama's library). Runtimes earn 25, with released llama.cpp (b11963), Ollama (v0.40.14, pinning b11963), vLLM, LM Studio and Transformers all running it. Builds earn nothing, because Ai2 publishes no quantised build of its own. Terms earn 10, since the card binds Apache 2.0 to Ai2's Responsible Use Guidelines, a use policy. Download earns 10, with no gate. Hosted earns nothing, as the Hub's provider mapping is empty and Ai2 has no API for it. 30 + 25 + 0 + 10 + 10 + 0 = 75.); 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. Runtimes 0, no released runtime runs the ricursive architecture with its own code; Ricursive's SGLang plugin and Transformers' remote code don't count. Builds 10, one quantised precision (NVFP4) from Ricursive. Terms 15, Apache 2.0 with nothing added. Download 10, not gated. Hosted 0, Ricursive serves no API, Hugging Face maps no provider, Together AI's page says coming soon, and GMI Cloud's and OpenRouter's pages weren't read.)
- Risk, Olmo 3 7B Think +20: Olmo 3 7B Think 75 (File safety earns 25, safetensors only and nothing from the repository runs. Provenance earns 15, files in the allenai organisation Ai2 links to, with a checksum for every file. Safety evaluation earns 20, as Ai2 publishes its safety results and the OLMES harness to rerun them. Agent guidance earns 5 for the card's general cautions. Licence risk earns 5, losing 5 for disallowed uses beyond the law and 5 because Ai2 can update the guidelines and end access at its discretion. The security programme earns 5 for a reporting route, a security.txt now past its expiry and a channel for security concerns in the guidelines, with no public advisories. 25 + 15 + 20 + 5 + 5 + 5 = 75.); Ripple-65B Preview 55 (File safety 15, safetensors only, less 10 because the documented way to run it loads Ricursive's Python. Provenance 15, the files are in the organisation ricursive.com links to, with a checksum on every file. Safety evaluation 10, Ricursive's own FORTRESS and StrongREJECT results. Agent guidance 0, nothing on prompt injection, refusals or safeguards. Licence risk 15, Apache 2.0. Security programme 0, no way to report a flaw.)