# DiffusionGemma 26B A4B IT vs Ripple-65B Preview (slim)

> Ripple-65B Preview scores 53.3 (D) to DiffusionGemma 26B A4B IT's 51.3 (D) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-ripple-65b-preview.md (~8,550 tokens) · this version ~1,630 tokens · JSON https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-ripple-65b-preview.json · canonical https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-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)

Ripple-65B Preview scores 53.3 (D) on agent readiness against DiffusionGemma 26B A4B IT's 51.3 (D), and leads in 1 of 4 scored categories. DiffusionGemma 26B A4B IT leads on reach, risk and documentation and upkeep. Both do open-weight models you run yourself.

- DiffusionGemma 26B A4B IT: D 51.3, rank #110 of 121 open-weight models · https://www.anchorterminal.com/tools/diffusiongemma-26b-a4b-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
- DiffusionGemma 26B A4B IT, good for Agents with about 64 GB of GPU memory that want fast single-user generation from text and images and can accept lower quality than Gemma 4 Ahead on Reach, 55 against 45; Risk, 70 against 55; Documentation and upkeep, 60 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. Ahead on Agent interface, 75 against 70.

| Category | DiffusionGemma 26B A4B IT | Ripple-65B Preview |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 55 | 45 |
| Risk (20%) | 70 | 55 |
| Agent interface (10%) | 70 | 75 |
| Documentation and upkeep (10%) | 60 | 49 |

| Fact (where they differ) | DiffusionGemma 26B A4B IT | Ripple-65B Preview |
| --- | --- | --- |
| Vendor | Google DeepMind | Ricursive Intelligence |
| llms.txt | yes | no |
| Last release | 2026-07-15 | 2026-11-04 |
| Terms last updated | no document linked | not read yet |
| Agent reviews | 2.5/5 (4) | none |

Why the edge:
- Risk, DiffusionGemma 26B A4B IT +15: DiffusionGemma 26B A4B IT 70 (File safety gets the full 25, safetensors only and loaded by Transformers' own code and a Jinja template. Provenance gets 15 for files in Google's organisation with a hash for every file. Licence risk keeps 15 under plain Apache 2.0. Agent guidance gets 10 for the card's list of harm categories and its advice to add content-safety safeguards. Safety evaluation scores 0 because the card states improvements without figures. The security programme gets 5 for Google's security.txt, with no public advisories for Gemma.); 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.)
- Documentation and upkeep, DiffusionGemma 26B A4B IT +11: DiffusionGemma 26B A4B IT 60 (The card covers all seven points (20), and the training data is a general description with a January 2025 cut-off (10). The files last changed on 15 July 2026, 112 days before this check (10). Google organisation members answered 10 of the 20 discussions (10). It's a first release (5). File health gets 5 because the diffusers scheduler config disagrees with the card's sampling settings, though the files on the documented path agree.); 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.)
- Reach, DiffusionGemma 26B A4B IT +10: DiffusionGemma 26B A4B IT 55 (Memory earns 15 because the only Google build is 51.7 GB of BF16, about 62 GB with the fifth added, which needs the 64 GB band. Runtimes get 15 for Transformers from 5.11.0, SGLang from v0.5.22 and vLLM, whose releases from v0.24.0 (tag commit 28 June 2026) to v0.33.0 register DiffusionGemmaForBlockDiffusion; llama.cpp (b12114, and Ollama through its pin b11963) and LM Studio don't run it. Builds score 0 because Google publishes no quantised build, though others have published FP8, NVFP4, GGUF and 4-bit copies. Apache 2.0 with nothing added gives terms the full 15 and the ungated repository gives download the full 10. Hosted too scores 0, since no inference provider is mapped and the Gemini API doesn't serve 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, Ripple-65B Preview +5: DiffusionGemma 26B A4B IT 70 (The chat template is in the repository (20) and handles several tool calls in one turn, and the card names function calling as trained (20). The tool-calling format gets 10, since only the template and the shipped response schema say how tools work here and Google's tool-calling guide is for Gemma 4. Structured output scores 0, undocumented and rejected by SGLang. Thinking can be turned on or off per request with the reasoning in its own channel (10), and the context is 256K (10).); 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.)