# GLM-4.7-Flash vs Ripple-65B Preview (slim)

> GLM-4.7-Flash scores 63 (B) 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/glm-4-7-flash-vs-ripple-65b-preview.md (~7,650 tokens) · this version ~1,330 tokens · JSON https://www.anchorterminal.com/compare/glm-4-7-flash-vs-ripple-65b-preview.json · canonical https://www.anchorterminal.com/compare/glm-4-7-flash-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)

GLM-4.7-Flash scores 63 (B) on agent readiness against Ripple-65B Preview's 53.3 (D), and leads in 2 of 4 scored categories. Ripple-65B Preview leads on documentation and upkeep. Both do open-weight models you run yourself.

- GLM-4.7-Flash: B 63, rank #26 of 121 open-weight models · https://www.anchorterminal.com/tools/glm-4-7-flash.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
- GLM-4.7-Flash, good for Agents and developers who want a small, permissively licensed tool-calling model on one 24 to 32 GB GPU or Mac, in almost any runtime Ahead on Reach, 80 against 45; Agent interface, 85 against 75.
- 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 Documentation and upkeep, 49 against 28.

| Category | GLM-4.7-Flash | Ripple-65B Preview |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 80 | 45 |
| Risk (20%) | 55 | 55 |
| Agent interface (10%) | 85 | 75 |
| Documentation and upkeep (10%) | 28 | 49 |

| Fact (where they differ) | GLM-4.7-Flash | Ripple-65B Preview |
| --- | --- | --- |
| Vendor | Z.ai (Zhipu AI) | Ricursive Intelligence |
| Licence | MIT | Apache-2.0 |
| Last release | 2026-01-29 | 2026-11-04 |
| Terms last updated | no document linked | not read yet |
| Agent reviews | 2.8/5 (4) | none |

Why the edge:
- Reach, GLM-4.7-Flash +35: GLM-4.7-Flash 80 (Memory earns 25, since Ollama's smallest build is the 19 GB q4_K_M one, about 22.8 GB with the fifth added, which fits 24 GB. Runtimes reach the cap of 25, with model code in released vLLM, SGLang and Transformers, a converter in a released llama.cpp build and a local entry in Ollama's library. Builds earn nothing, because Z.ai publishes only BF16 and every quantised build is someone else's. The MIT licence with nothing added gives the full 15 for terms, the files download with no account or gate for 10, and Z.ai plus three other providers serve it for 5.); 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 +21: GLM-4.7-Flash 28 (The card covers architecture, parameters and languages and misses four of the seven items, for 8. Training data is 0, as the card describes none. The last change was on 1 February 2026 at the latest, within a year but past 180 days, for 5. Responsiveness is 5, since zai-org answered 6 of the 40 most recent discussions, all by 31 January, which is a few. Version policy is 5 for a first release with no files replaced, and file health is 5, as config.json and tokenizer_config.json disagree on context and a config report waits without a reply.); 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, GLM-4.7-Flash +10: GLM-4.7-Flash 85 (A Jinja chat template sits in the repository, for 20. The tool-calling format is the full 25, because Z.ai itself names the glm47 parser for vLLM and SGLang, says tools are declared in OpenAI style and shows calls coming back as tool_calls. The template takes several calls in one turn, for 20. Structured output is 0, with nothing on the card and only the hosted API documented for JSON. Reasoning control is 10, thinking turned off per request with enable_thinking and the reasoning returned by the glm45 parser. Context is 10, 202,752 positions native with no rope 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.)