DiffusionGemma 26B A4B IT vs Step 3.7 Flash

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.

Step 3.7 Flash 45

File safety 15, safetensors and GGUF only, no .bin, .pt or .pth files (25). Provenance 15, the files sit in the stepfun-ai organisation, which the card's StepFun platform and model page belong to (10). Safety evaluation 0, no safety results on the card. Agent guidance 0, the card has no limitations section and gives no guidance on prompt injection, instruction priority, refusals or safeguards. Licence risk 15, Apache 2.0 has no use policy, threshold or change clause. Security programme 0, no way to report a flaw on the card, and our StepFun API listing found no security.txt, bug bounty or disclosure policy. 15 + 15 + 0 + 0 + 15 + 0 = 45.

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.

Step 3.7 Flash 39

Model card 14, Intended use, the architecture, the parameters, the context and the language (in the metadata) are on the card. Training data 0, Nothing on the card about the training data. Last change 10, the last commit, on 3 June 2026, fixed the modelling code, 160 days before this check and within 180. Responsiveness 0, none of the 11 most recent discussions that aren't pull requests (29 May to 24 June 2026) has a reply from a stepfun-ai member, counted on 10 November by author flags and dates with a script, text not read. Version policy 5, Step-3.5-Flash stays in its own repositories and 3.7 came out in new ones, with no dated note on the older cards that we read. File health 10, Config, template and card agree on the architecture and the context, and June commits fixed the modelling code. 14 + 0 + 10 + 0 + 5 + 10 = 39.

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.

Step 3.7 Flash 70

Memory 5, the smallest build at 4 bits is StepFun's IQ4_XS GGUF, 104.99 GB with the 3.97 GB projector, and 108.96 GB × 1.2 = 130.8 GB, over what the reference machine can give a model and within 256 GB. The IQ3 and Q3 builds are below 4 bits and aren't read. Runtimes 20, Released vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 have the step3p7 model, and llama.cpp b12242 has the architecture, with StepFun's own GGUF. Four at 5 each, and the card documents all four. Builds 15, StepFun publishes GGUF at five quantised precisions, an FP8 build and an NVFP4 build. Terms 15, Apache 2.0 in the card's metadata and its licence section, an OSI licence with nothing added. Download 10, the Hub API reports gated false for all four repositories on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, StepFun's own API serves it, per the card and our StepFun API listing, and Featherless and DeepInfra are live for it on Hugging Face. 5 + 20 + 15 + 15 + 10 + 5 = 70.

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).

Step 3.7 Flash 85

Chat template 20, chat_template.jinja in the repository (5,723 characters). Tool-calling format 25, the card names the parser to use in two runtimes, step3p5 in vLLM (with auto tool choice) and in SGLang, and both ship Step parsers in a release. Trained tool calling 20, the card presents tool orchestration as a main use, with multi-turn results, and the template renders every call in a turn. Structured output 0, Nothing on the card about JSON or schema-constrained output for the weights. Reasoning control 10, the template has a reasoning_effort setting and keeps reasoning_content, and the card names the step3p5 reasoning parser for vLLM and SGLang, which returns the reasoning apart from the answer. Context 10, 256K tokens per the card, and 262,144 positions in config.json. 20 + 25 + 20 + 0 + 10 + 10 = 85.