# Qwen3.5-4B vs Ripple-65B Preview (slim)

> Qwen3.5-4B scores 61.2 (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/qwen3-5-4b-vs-ripple-65b-preview.md (~7,450 tokens) · this version ~1,330 tokens · JSON https://www.anchorterminal.com/compare/qwen3-5-4b-vs-ripple-65b-preview.json · canonical https://www.anchorterminal.com/compare/qwen3-5-4b-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)

Qwen3.5-4B scores 61.2 (C) on agent readiness against Ripple-65B Preview's 53.3 (D), and leads in 1 of 4 scored categories. Ripple-65B Preview leads on agent interface and documentation and upkeep. Both do open-weight models you run yourself.

- Qwen3.5-4B: C 61.2, rank #38 of 121 open-weight models · https://www.anchorterminal.com/tools/qwen3-5-4b.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
- Qwen3.5-4B, good for Agents that want a cheap local helper for tool calls, short reasoning and reading images on a laptop or small GPU Ahead on Reach, 85 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 70; Documentation and upkeep, 49 against 34.

| Category | Qwen3.5-4B | Ripple-65B Preview |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 85 | 45 |
| Risk (20%) | 55 | 55 |
| Agent interface (10%) | 70 | 75 |
| Documentation and upkeep (10%) | 34 | 49 |

| Fact (where they differ) | Qwen3.5-4B | 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, Qwen3.5-4B +40: Qwen3.5-4B 85 (Memory earns the full 30 because Ollama's own Q4_K_M build is 3.3 GB, about 4 GB with the fifth added, though Alibaba itself publishes no quantised 4B, so builds scores 0. Runtimes reach the 25 cap on vLLM's stable release, Transformers 5.2.0, llama.cpp, Ollama's library and LM Studio's catalogue. Apache 2.0 with nothing added gives the full 15 for terms, the ungated repository the full 10 for download, and two providers (featherless-ai, live on Hugging Face on 2 November, and Doubleword's own list per the 21 October check) the 5 for hosted too. 30 + 25 + 0 + 15 + 10 + 5 = 85.); 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.)
- Documentation and upkeep, Ripple-65B Preview +15: Qwen3.5-4B 34 (The card covers five of the seven items and misses limitations and a cut-off (14). Training data is a general description without a cut-off (5). The files last changed on 2 March 2026, 245 days before 2 November, which is within a year (5). No Qwen member has answered any of the 21 discussions that aren't pull requests, four of them opened since 21 October (0), and the GitHub issues couldn't be counted. Earlier 4B models stay in their own repositories without dated notes (5), and two pull requests fixing the template and adding generation_config.json wait unanswered (5). 14 + 5 + 5 + 0 + 5 + 5 = 34.); 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.)
- Agent interface, Ripple-65B Preview +5: Qwen3.5-4B 70 (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 declaration and call format to the template. Thinking turns off per request and comes back in think tags split by the qwen3 parser (10), and 262,144 tokens is native (10). Structured output scores 0, as nothing documents JSON output for the model.); 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.)