# Nanbeige4.2-3B vs Ripple-65B Preview (slim)

> Nanbeige4.2-3B scores 61 (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/nanbeige-4-2-3b-vs-ripple-65b-preview.md (~9,550 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/nanbeige-4-2-3b-vs-ripple-65b-preview.json · canonical https://www.anchorterminal.com/compare/nanbeige-4-2-3b-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)

Nanbeige4.2-3B scores 61 (C) on agent readiness against Ripple-65B Preview's 53.3 (D), and leads in 3 of 4 scored categories. Both do open-weight models you run yourself.

- Nanbeige4.2-3B: C 61, rank #78 of 160 open-weight models · https://www.anchorterminal.com/tools/nanbeige-4-2-3b.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
- Nanbeige4.2-3B, good for Local agents that need tool calling and a long context on a laptop or a small GPU Ahead on Reach, 85 against 45; Agent interface, 85 against 75; Documentation and upkeep, 72 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.

| Category | Nanbeige4.2-3B | Ripple-65B Preview |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 85 | 45 |
| Risk (20%) | 55 | 55 |
| Agent interface (10%) | 85 | 75 |
| Documentation and upkeep (10%) | 72 | 49 |

| Fact (where they differ) | Nanbeige4.2-3B | Ripple-65B Preview |
| --- | --- | --- |
| Vendor | Nanbeige LLM Lab (BOSS Zhipin) | Ricursive Intelligence |
| Licence | Apache-2.0 (Hub metadata only; the repository has no LICENSE file) | Apache-2.0 |
| Last release | 2026-09-11 | 2026-11-04 |
| Terms last updated | no document linked | not read yet |

Why the edge:
- Reach, Nanbeige4.2-3B +40: Nanbeige4.2-3B 85 (Memory 30, the smallest build from Nanbeige is the FP8 repository (the 8-bit GPTQ one is the same size), 5.19 GB, and 5.19 GB × 1.2 = 6.2 GB, within 16 GB.); 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.)
- Documentation and upkeep, Nanbeige4.2-3B +23: Nanbeige4.2-3B 72 (Model card 17, Intended use, limitations, the architecture, the parameters (3B outside the embeddings), the context and the languages (in the metadata) are on t…); Ripple-65B Preview 49 (Model card 14 of 20, no limitations and no knowledge cut-off.)
- Agent interface, Nanbeige4.2-3B +10: Nanbeige4.2-3B 85 (Chat template 20, A Jinja chat template in tokenizer_config.json (7,961 characters), with enable_thinking, preserve_thinking, tools and tool_call_format switche…); Ripple-65B Preview 75 (Chat template 20, chat_template.jinja in the repository.)