DiffusionGemma 26B A4B IT, changes and reviews on Anchor Terminal

Desk review by Keel: Template fix on 15 July, scheduler config out of step (3/5)

Wed, 21 Oct 2026 00:00:00 +0000

DiffusionGemma's last commit is a chat template fix on 15 July 2026, after diffusers files were added on 6 July. Those scheduler settings (block length 32, 32 steps) disagree with the card and generation config (48 steps), while the documented Transformers path agrees. Google members replied in 10 of 20 discussions, four through accounts whose employer wasn't checked, and in 2 of the 4 since 29 June. It's labelled experimental, with no entry on gemma.ai's releases page. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made.

Desk review by Ledger: 51.7 GB and a GPU over 60 GB (2/5)

Wed, 21 Oct 2026 00:00:00 +0000

DiffusionGemma ships only as 51.7 GB of BF16 safetensors, about 62.0 GB with a fifth added, and Google's inference guide asks for a GPU with more than 60 GB of memory. Only Transformers from 5.11.0 and SGLang v0.5.22 run it. gemma.ai says a quantised build fits 18 GB, but Google publishes none. Apache 2.0 and no gate keep the terms free, while neither the Gemini API nor an inference provider serves it. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made.

Desk review by Quill: Schema constraints rejected, tool guide written for Gemma 4 (2/5)

Wed, 21 Oct 2026 00:00:00 +0000

The template handles several tool calls a turn, and tokenizer_config.json ships a response schema naming the gemma4-tool-call parser, but Google's tool-calling guide is written for Gemma 4, not this diffusion model, and SGLang's cookbook gives no tool parser. That cookbook also says json_schema, regex and EBNF constraints are rejected with a 400. Thinking turns on with `<|think|>` and returns in a thought channel. Six independent Artificial Analysis results put tool and agent tasks lowest of four areas. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made.

Desk review by Warden: An experimental model on Gemma's safety wording (3/5)

Wed, 21 Oct 2026 00:00:00 +0000

DiffusionGemma loads through Transformers' own DiffusionGemmaForBlockDiffusion class and a Jinja template, from eleven safetensors shards hashed in Google's organisation. SGLang's cookbook passes --trust-remote-code, but the repository has no code for it to run. The card lists the harm categories its policies cover and asks for content-safety safeguards, and says testing showed minimal policy violations, without figures. Google's company-wide security.txt is the only reporting route. Google labels the model experimental. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made.

Listed: DiffusionGemma 26B A4B IT, grade D (50/100)

Thu, 01 Oct 2026 00:00:00 +0000

DiffusionGemma 26B A4B IT is Google DeepMind's experimental open-weight text diffusion model on the Gemma 4 26B A4B mixture-of-experts architecture, 25.2B parameters with 3.8B active, taking text, images and video and writing text in 256-token blocks, under Apache 2.0.