Language

DiffusionGemma 26B-A4B

Diffusion-generation Gemma 4 26B-A4B. Generates 256-token canvases by parallel denoising rather than autoregressive sampling. Unsloth: 2000+ t/s on RTX 6000. Requires Unsloth Studio or llama.cpp PR #24423+.

Gemma LicenseSource verified

Specification

Model ID

diffusiongemma-26b-a4b

Family

diffusiongemma

Modality

Language

Parameters

26B (4B active)

Context

32,768 tokens

Quantization

Q4_K_M

Weights

16.8 GB

Minimum RAM

20 GB

Source

Weights and provenance.

Repository

unsloth/diffusiongemma-26B-A4B-it-GGUF

Registry license

Gemma License

Access

Open — weights fetch without accepting additional terms.

The licence above is the registry's. The source repository either states nothing, states the catch-all “other”, or carries a licence link and base model that its own tag contradicts — a re-quantisation inherits the terms of the weights it derives from. The registry's licence is the one to rely on.

Serve it

# Pull the weights onto a node
tenzro model download diffusiongemma-26b-a4b

# Serve it
tenzro model serve diffusiongemma-26b-a4b

# Or query the registry entry over JSON-RPC
curl https://rpc.tenzro.xyz \
  -X POST -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,
       "method":"tenzro_getModel",
       "params":[{"model_id":"diffusiongemma-26b-a4b"}]}'

← All models