# Nanbeige4.3-33B vs Ripple-65B Preview (slim)

> Nanbeige4.3-33B scores 60.8 (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-4-3-33b-vs-ripple-65b-preview.md (~8,100 tokens) · this version ~1,530 tokens · JSON https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-ripple-65b-preview.json · canonical https://www.anchorterminal.com/compare/nanbeige-4-3-33b-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)

Nanbeige4.3-33B scores 60.8 (C) on agent readiness against Ripple-65B Preview's 53.3 (D), and leads in every scored category. Both do open-weight models you run yourself.

- Nanbeige4.3-33B: C 60.8, rank #61 of 121 open-weight models · https://www.anchorterminal.com/tools/nanbeige-4-3-33b.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
- Nanbeige4.3-33B, good for Agents with a 32 GB GPU (INT4) or more, or the 128 GB reference machine at BF16, that want an Apache-tagged 33B model for long coding and tool loops. Ahead on Reach, 80 against 45; Risk, 60 against 55; Agent interface, 85 against 75; Documentation and upkeep, 56 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 | Nanbeige4.3-33B | Ripple-65B Preview |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 80 | 45 |
| Risk (20%) | 60 | 55 |
| Agent interface (10%) | 85 | 75 |
| Documentation and upkeep (10%) | 56 | 49 |

| Fact (where they differ) | Nanbeige4.3-33B | 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 | 2026-10-31 | 2026-11-04 |
| Terms last updated | no document linked | not read yet |

Why the edge:
- Reach, Nanbeige4.3-33B +35: Nanbeige4.3-33B 80 (Memory earns 20, since Nanbeige's INT4 build is 22.57 GB, about 27 GB with a fifth added, which fits 32 GB. Runtimes earn 20 from released vLLM, SGLang, Transformers and llama.cpp, which all run the Llama architecture, and Ollama and LM Studio have no build. Builds earn 15 for Nanbeige's INT4, INT8 and FP8 builds of 31 October 2026. Terms earn 15 for Apache 2.0 with nothing added, though only the metadata names it. Download earns 10, with no gate. Hosted earns 0, as no provider or Nanbeige API serves it.); 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, Nanbeige4.3-33B +10: Nanbeige4.3-33B 85 (The chat template earns 20, Jinja in tokenizer_config.json. The tool-calling format earns 25, with the XML call format in the template and the qwen3_coder parser named for vLLM and SGLang. Trained tool calling earns 20, several calls per turn in the template. Structured output earns 0, as nothing mentions it. Reasoning control earns 10, thinking switched per request with the qwen3 reasoning parser named. Context earns 10 for 512K set in the config with no scaling.); 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, Nanbeige4.3-33B +7: Nanbeige4.3-33B 56 (The model card earns 11, with intended use, parameters, context and languages but no limitations, architecture or cut-off. Training data earns 0, as nothing describes it. Last change earns 20 for the quantised builds of 31 October 2026. Responsiveness earns 10, a Nanbeige member answering nine of 30 discussions. Version policy earns 5 for a first release, with a config change made and reverted under bare commit titles. File health earns 10, the files and the card agreeing.); 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, Nanbeige4.3-33B +5: Nanbeige4.3-33B 60 (File safety earns 25, safetensors only and no repository code, so the card's trust_remote_code has nothing to run. Provenance earns 15, the lab's own organisation as its arXiv report links it, with a hash for every file. Safety evaluation earns 0 and agent guidance 0, since neither card says anything on either. Licence risk keeps all 15 under Apache 2.0. The security programme earns 5 for BOSS Zhipin's security response centre, which isn't linked to the model.); 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.)