Instructions to use AlexAtomic/diffusiongemma-26B-A4B-it-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AlexAtomic/diffusiongemma-26B-A4B-it-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AlexAtomic/diffusiongemma-26B-A4B-it-GGUF",
	filename="diffusiongemma-26B-A4B-it-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use AlexAtomic/diffusiongemma-26B-A4B-it-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AlexAtomic/diffusiongemma-26B-A4B-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AlexAtomic/diffusiongemma-26B-A4B-it-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AlexAtomic/diffusiongemma-26B-A4B-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AlexAtomic/diffusiongemma-26B-A4B-it-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf AlexAtomic/diffusiongemma-26B-A4B-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AlexAtomic/diffusiongemma-26B-A4B-it-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf AlexAtomic/diffusiongemma-26B-A4B-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AlexAtomic/diffusiongemma-26B-A4B-it-GGUF:Q4_K_M

Use Docker

docker model run hf.co/AlexAtomic/diffusiongemma-26B-A4B-it-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use AlexAtomic/diffusiongemma-26B-A4B-it-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AlexAtomic/diffusiongemma-26B-A4B-it-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlexAtomic/diffusiongemma-26B-A4B-it-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AlexAtomic/diffusiongemma-26B-A4B-it-GGUF:Q4_K_M

Ollama
How to use AlexAtomic/diffusiongemma-26B-A4B-it-GGUF with Ollama:
```
ollama run hf.co/AlexAtomic/diffusiongemma-26B-A4B-it-GGUF:Q4_K_M
```

Unsloth Studio

How to use AlexAtomic/diffusiongemma-26B-A4B-it-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for AlexAtomic/diffusiongemma-26B-A4B-it-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for AlexAtomic/diffusiongemma-26B-A4B-it-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AlexAtomic/diffusiongemma-26B-A4B-it-GGUF to start chatting

How to use AlexAtomic/diffusiongemma-26B-A4B-it-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AlexAtomic/diffusiongemma-26B-A4B-it-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "AlexAtomic/diffusiongemma-26B-A4B-it-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AlexAtomic/diffusiongemma-26B-A4B-it-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AlexAtomic/diffusiongemma-26B-A4B-it-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default AlexAtomic/diffusiongemma-26B-A4B-it-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use AlexAtomic/diffusiongemma-26B-A4B-it-GGUF with Docker Model Runner:
```
docker model run hf.co/AlexAtomic/diffusiongemma-26B-A4B-it-GGUF:Q4_K_M
```

Lemonade

How to use AlexAtomic/diffusiongemma-26B-A4B-it-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AlexAtomic/diffusiongemma-26B-A4B-it-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.diffusiongemma-26B-A4B-it-GGUF-Q4_K_M

List all available models

lemonade list

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).

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

Download google/diffusiongemma-26B-A4B-it.
Convert to f16 GGUF with the DiffusionGemma build of llama.cpp.
Verify generation with llama-diffusion-cli.
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.

Downloads last month: 358

GGUF

Model size

25B params

Architecture

diffusion-gemma

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

Model tree for AlexAtomic/diffusiongemma-26B-A4B-it-GGUF

Base model

google/diffusiongemma-26B-A4B-it

Quantized

(22)

this model