← Catalog
DiffusionGemma 26B-A4B
AvailableGoogle DeepMindOpen source
An open-weight text-diffusion model built on the Gemma 4 26B-A4B MoE backbone (25.2B total / 3.8B active). Denoises text in parallel 256-token blocks for up to ~4x faster generation (1,000+ tok/s on an H100), with a 256K context and text, image, and video input. Apache-2.0.
Specifications
- License
- Open source · Apache-2.0
- Weights
- Downloadable
- Architecture
- Mixture-of-Experts
- Parameters
- 25.2B · 3.8B active
- Context window
- 256K tokens
- Max output
- —
- Knowledge cutoff
- —
- Price (in / out, $/M)
- —
- Modalities
- TextVisionVideoCode
Benchmarks
No benchmark scores recorded yet. Spotted some? Submit a correction.
Vendor-reported figures are claims until independently verified. See methodology.