# Cosmos-Reason2-2B vs Ripple-65B Preview (slim)

> Cosmos-Reason2-2B scores 59.5 (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/cosmos-reason2-2b-vs-ripple-65b-preview.md (~8,250 tokens) · this version ~1,780 tokens · JSON https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-ripple-65b-preview.json · canonical https://www.anchorterminal.com/compare/cosmos-reason2-2b-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)

Cosmos-Reason2-2B scores 59.5 (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 and documentation and upkeep. Both do open-weight models you run yourself.

- Cosmos-Reason2-2B: C 59.5, rank #69 of 121 open-weight models · https://www.anchorterminal.com/tools/cosmos-reason2-2b.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
- 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 45; Risk, 60 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 65; Documentation and upkeep, 49 against 39.

| Category | Cosmos-Reason2-2B | Ripple-65B Preview |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 45 |
| Risk (20%) | 60 | 55 |
| Agent interface (10%) | 65 | 75 |
| Documentation and upkeep (10%) | 39 | 49 |

| Fact (where they differ) | Cosmos-Reason2-2B | Ripple-65B Preview |
| --- | --- | --- |
| Vendor | NVIDIA | Ricursive Intelligence |
| 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 | 2026-11-04 |
| Terms last updated | 2025-10-24 | not read yet |
| 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:
- Reach, Cosmos-Reason2-2B +20: 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. Runtimes get 20 because the model keeps Qwen3-VL's architecture, which Transformers, vLLM, SGLang and llama.cpp run in released versions, while LM Studio's catalogue has only the base. Builds score 0, as NVIDIA publishes no quantised build of the 2B. The NVIDIA Open Model License allows free commercial use under a use policy (10). The gate is an automatic click-through that needs an account (5), and nothing hosts the 2B (0).); 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.)
- Agent interface, Ripple-65B Preview +10: Cosmos-Reason2-2B 65 (A Jinja template ships as chat_template.json (20). Tools are declared only by the template it inherits from Qwen3-VL, with no NVIDIA documentation or parser (10), and nothing shows the 2B was trained for tool use (0). NVIDIA's prompt files ask for JSON with named keys for boxes, events and trajectories (15). Reasoning is asked for in the prompt and vLLM's qwen3 parser returns it apart (10). The card states 256K input tokens (10).); 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.)
- Documentation and upkeep, Ripple-65B Preview +10: Cosmos-Reason2-2B 39 (The card misses languages and a cut-off (14). Training data is named by dataset without sizes or a cut-off (5). The Hub repository last changed on 30 April 2026, 188 days before this check, which alone gives 5. NVIDIA's GitHub repository last changed with a README redirect to Cosmos 3 on 7 June 2026, 150 days back, and this run counts the publisher's documentation commits on this line (10). None of its 3 discussions has an NVIDIA reply, counted by author flags on 4 November (0). The 2B's weights were replaced in place in March with a dated line, and the family is now superseded by Cosmos 3 with a dated note (5). The gated files couldn't be checked against the card, which itself mixes float16 and BF16 and links a newer licence than the gate shows (5). 14 + 5 + 10 + 0 + 5 + 5 = 39.); Ripple-65B Preview 49 (Model card 14 of 20, no limitations and no knowledge cut-off. Training data 5, a general description with token counts and no cut-off. Last change 20, released today. Responsiveness 0, no discussions yet, read as none answered. Version policy 5, a first release, with the NVFP4 checkpoint replaced in place on release day under a commit note. File health 5, tokenizer_config.json carries a second, tool-less chat template and a 131,072-token limit against the card's 1M.)
- Risk, Cosmos-Reason2-2B +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. Provenance gets 15 for files in NVIDIA's own organisation with hashes. The licence has a use policy and guardrail clause and NVIDIA can revoke or update it, so licence risk keeps 5 of 15. NVIDIA's PSIRT route and bulletins give the security programme 10. Agent guidance gets 5 for general cautions about guardrails and physical risk, and safety evaluation 0, with no safety results.); 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.)