# Qwen3.5-2B vs Ripple-65B Preview (slim)

> Ripple-65B Preview scores 53.3 (D) to Qwen3.5-2B's 50.5 (D) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/qwen3-5-2b-vs-ripple-65b-preview.md (~7,450 tokens) · this version ~1,280 tokens · JSON https://www.anchorterminal.com/compare/qwen3-5-2b-vs-ripple-65b-preview.json · canonical https://www.anchorterminal.com/compare/qwen3-5-2b-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)

Ripple-65B Preview scores 53.3 (D) on agent readiness against Qwen3.5-2B's 50.5 (D), and leads in 2 of 4 scored categories. Qwen3.5-2B leads on reach. Both do open-weight models you run yourself.

- Qwen3.5-2B: D 50.5, rank #111 of 121 open-weight models · https://www.anchorterminal.com/tools/qwen3-5-2b.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
- Qwen3.5-2B, good for Builders who want a cheap local helper or fine-tuning base for narrow tasks and image reading on a laptop, small GPU or CPU Ahead on Reach, 80 against 45.
- 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; Documentation and upkeep, 49 against 37.

| Category | Qwen3.5-2B | Ripple-65B Preview |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 80 | 45 |
| Risk (20%) | 55 | 55 |
| Agent interface (10%) | 60 | 75 |
| Documentation and upkeep (10%) | 37 | 49 |

| Fact (where they differ) | Qwen3.5-2B | Ripple-65B Preview |
| --- | --- | --- |
| Vendor | Alibaba (Qwen team) | Ricursive Intelligence |
| Last release | 2026-03-02 | 2026-11-04 |
| Terms last updated | no document linked | not read yet |
| Agent reviews | 3/5 (4) | none |

Why the edge:
- Reach, Qwen3.5-2B +35: Qwen3.5-2B 80 (Memory earns the full 30, since LM Studio's Q4_K_M GGUF with its vision projector is 1.94 GB, about 2.3 GB with the fifth added (Ollama's Q4_K_M build was 1.9 GB on 21 October). Alibaba publishes no quantised 2B, so builds scores 0. Runtimes reach the 25 cap, with llama.cpp b11963 and Ollama through the build it pins re-read today. Apache 2.0 with nothing added gives terms 15 and the ungated download 10. Hosted too scores 0, as only Featherless AI is in the Hub's provider mapping and the line needs two. 30+25+0+15+10+0 = 80.); 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 +15: Qwen3.5-2B 60 (The template ships in the repository (20) and the model was trained for tool use with several calls per turn in the template (20). Tool-calling format gets 10, because the card names the qwen3_coder parser but leaves the format to the template. Reasoning control scores 0, since the card shows how to turn thinking on but not where the reasoning comes back. 262,144 tokens is native (10). Structured output scores 0, as nothing documents JSON output for the model. 20+10+20+0+0+10 = 60.); 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 +12: Qwen3.5-2B 37 (The card covers six of the seven items, missing only a cut-off (17), because it states the intended uses and warns about thinking loops. Training data is a general description without a cut-off (5). The files last changed on 2 March 2026, 247 days before 4 November, within a year (5). No Qwen member has answered any of the 6 discussions that aren't pull requests (0). Qwen3-1.7B stays in its own repository without a dated note (5), and a template fix and the missing generation_config.json wait unanswered (5). 17+5+5+0+5+5 = 37.); 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.)