---

license: gemma

license_link: https://ai.google.dev/gemma/terms

base_model:

• google/diffusiongemma-26B-A4B-it

base_model_relation: quantized

quantized_by: AlexAtomic

language:

• en

pipeline_tag: text-generation

library_name: gguf

tags:

• atomic-chat
• gemma
• diffusion-gemma
• diffusion-lm
• gguf
• quantized
• llama.cpp

---

Atomic Chat · DiffusionGemma 26B-A4B (GGUF)

GGUF quantizations of google/diffusiongemma-26B-A4B-it, self-quantized by Atomic Chat from Google's original weights.

This is a discrete diffusion language model. It does not generate token by token. It denoises a block of tokens (a "canvas") in parallel using block-autoregressive multi-canvas sampling. It is also a sparse MoE: 25.2B total parameters, 3.8B active (8 of 128 experts).

> [!WARNING]

> These run only with the DiffusionGemma build of llama.cpp, via the dedicated llama-diffusion-cli runner. The standard llama-cli / llama-server, Ollama, LM Studio and Jan cannot run these yet. Diffusion support is an open draft PR (ggml-org/llama.cpp#24423), not yet merged to master.

Quants

| Quant | Size | Notes |

|---|---|---|

| Q4_K_M | ~16.8 GB | Recommended default. Best size / quality balance. |

| Q5_K_M | ~19.1 GB | Higher quality. |

| Q6_K | ~22.7 GB | Near lossless. |

| Q8_0 | ~26.9 GB | Effectively lossless, reference quality. |

Quantized without an importance matrix (imatrix tooling does not yet cover diffusion decoding), matching the upstream approach.

How to run

Build the DiffusionGemma branch of llama.cpp:

git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp
git fetch origin pull/24423/head:diffusiongemma
git checkout diffusiongemma
cmake -B build -DGGML_CUDA=ON
cmake --build build -j --config Release --target llama-diffusion-cli

Generate:

./build/bin/llama-diffusion-cli \
    -hf AlexAtomic/diffusiongemma-26B-A4B-it-GGUF:Q4_K_M \
    -p "Explain what a neural network is in two sentences." \
    --diffusion-steps 128 --diffusion-visual

Set -DGGML_CUDA=OFF for CPU or Metal builds. Add -ngl N to offload N layers to GPU.

Useful diffusion flags:

• --diffusion-steps N denoising steps (default 128, fewer is faster).
• --diffusion-eb auto|on|off entropy-bound decoder tuned for DiffusionGemma.
• --diffusion-visual watch the canvas fill in progressively.

Model Overview

| Property | Value |

|---|---|

| Base model | google/diffusiongemma-26B-A4B-it |

| Architecture | diffusion-gemma (DiffusionGemmaForBlockDiffusion) |

| Total parameters | 25.2B |

| Active parameters | 3.8B (8 of 128 experts) |

| Generation | block-autoregressive diffusion (parallel denoising) |

| This repo | GGUF quants for llama-diffusion-cli |

How these were made

1. Download google/diffusiongemma-26B-A4B-it.
2. Convert to f16 GGUF with the DiffusionGemma build of llama.cpp.
3. Verify generation with llama-diffusion-cli.
4. Quantize the ladder with llama-quantize.

License

These weights are derived from Gemma and stay governed by the Gemma Terms of Use. By downloading you agree to those terms. Original model by Google DeepMind. Quantized by Atomic Chat.