# Gemma 4 31B IT vs Ripple-65B Preview (slim)

> Gemma 4 31B IT scores 74.1 (BB) 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/gemma-4-31b-it-vs-ripple-65b-preview.md (~7,950 tokens) · this version ~1,630 tokens · JSON https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-ripple-65b-preview.json · canonical https://www.anchorterminal.com/compare/gemma-4-31b-it-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)

Gemma 4 31B IT scores 74.1 (BB) 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.

- Gemma 4 31B IT: BB 74.1, rank #2 of 121 open-weight models · https://www.anchorterminal.com/tools/gemma-4-31b-it.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
- Gemma 4 31B IT, good for An agent with a 24 GB GPU or more that wants a dense multimodal cousin with tool calling under a plain licence Ahead on Reach, 95 against 45; Risk, 70 against 55; Agent interface, 85 against 75; Documentation and upkeep, 65 against 49. Also Agent-ready, a grade of BB or better.
- 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 | Gemma 4 31B IT | Ripple-65B Preview |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 95 | 45 |
| Risk (20%) | 70 | 55 |
| Agent interface (10%) | 85 | 75 |
| Documentation and upkeep (10%) | 65 | 49 |

| Fact (where they differ) | Gemma 4 31B IT | Ripple-65B Preview |
| --- | --- | --- |
| Vendor | Google DeepMind | Ricursive Intelligence |
| llms.txt | yes | no |
| Last release | 2026-07-20 | 2026-11-04 |
| Terms last updated | no document linked | not read yet |
| Agent reviews | 3.8/5 (4) | none |

Why the edge:
- Reach, Gemma 4 31B IT +50: Gemma 4 31B IT 95 (Memory 25, Google's own QAT Q4_0 GGUF is 17.7 GB, which with a fifth added comes to about 21 GB and fits a 24 GB card even with the vision projector. Runtimes 25, released code in llama.cpp, Ollama's library, vLLM, SGLang and Transformers fills the cap without LM Studio, which only Google's guides name. Builds 15, Google ships a 4-bit GGUF and a 4-bit compressed-tensors build, read as two of the kinds the checklist names. Terms 15, plain Apache 2.0 with nothing added. Download 10, no gate and no account. Hosted 5, Google's Gemini API serves it today.); 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, Gemma 4 31B IT +16: Gemma 4 31B IT 65 (Model card 20, all seven items are there, with languages given as counts. Training data 10, a general description with a January 2025 cut-off. Last change 10, the files last changed on 20 July, 104 days before 1 November, and Google's reference code for Gemma 4 last changed in a way that runs this model on 6 July, both inside 180 days. Responsiveness 10, Google answered 14 of the last 40 discussions, none since 30 July. Version policy 10, earlier generations are kept in their own repositories with dated releases. File health 5, two template reports wait 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.)
- Risk, Gemma 4 31B IT +15: Gemma 4 31B IT 70 (File safety 25, safetensors only and no code from the repository runs to load it or build prompts. Provenance 15, the files come from the google organisation that gemma.ai links to, with a SHA-256 for every weight file and a git hash for every file. Safety evaluation 0, Google says violations were minimal but publishes no results. Agent guidance 10, the card says what its safety training covers and asks for content safeguards, and the tool guide says to validate calls, but there is no prompt-injection guidance. Licence risk 15, Apache 2.0 carries none of the deductions and its link works. Security programme 5, Google's company-wide security.txt and reward programme exist but nothing ties them to Gemma, and no public advisories were found.); 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.)
- Agent interface, Gemma 4 31B IT +10: Gemma 4 31B IT 85 (Chat template 20, a Jinja file in the repository. Tool-calling format 25, Google documents the declaration and call syntax and ships a response schema that Transformers parses. Trained tool calling 20, several calls and responses in one turn. Structured output 0, Google documents none and the card doesn't claim it. Reasoning control 10, thinking turns on or off per request and comes back in its own block. Context 10, 262,144 tokens native.); 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.)