Instructions to use OsaurusAI/diffusiongemma-26B-A4B-it-MXFP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OsaurusAI/diffusiongemma-26B-A4B-it-MXFP8 with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("OsaurusAI/diffusiongemma-26B-A4B-it-MXFP8")
config = load_config("OsaurusAI/diffusiongemma-26B-A4B-it-MXFP8")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use OsaurusAI/diffusiongemma-26B-A4B-it-MXFP8 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/diffusiongemma-26B-A4B-it-MXFP8"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "OsaurusAI/diffusiongemma-26B-A4B-it-MXFP8"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use OsaurusAI/diffusiongemma-26B-A4B-it-MXFP8 with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/diffusiongemma-26B-A4B-it-MXFP8"

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 OsaurusAI/diffusiongemma-26B-A4B-it-MXFP8

Run Hermes

hermes

OpenClaw new

How to use OsaurusAI/diffusiongemma-26B-A4B-it-MXFP8 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/diffusiongemma-26B-A4B-it-MXFP8"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "OsaurusAI/diffusiongemma-26B-A4B-it-MXFP8" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

diffusiongemma-26B-A4B-it-MXFP8 / README.md

Osaurus-AI

Add DiffusionGemma MXFP8 bundle (vmlx block-diffusion engine)

163d543 verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

2.33 kB

metadata

license: gemma
base_model: google/diffusiongemma-26B-A4B-it
pipeline_tag: image-text-to-text
tags:
  - mlx
  - vmlx
  - osaurus
  - diffusion-language-model
  - block-diffusion
  - mxfp8
  - gemma
library_name: mlx

DiffusionGemma 26B-A4B-it — MXFP8 (Osaurus / vMLX)

Native MLX MXFP8 quantization of google/diffusiongemma-26B-A4B-it — a block-diffusion language model (NOT autoregressive): text generates as 256-token canvases refined by iterative denoising. 30-layer Gemma-4-style MoE, 128 experts top-8, 26B total / ~4B active parameters.

Runs natively in Osaurus on Apple Silicon via the vmlx-swift block-diffusion engine.

Quantization

Attention, dense MLP, router, and routed MoE experts: MXFP8 (group 32)
Embeddings, norms, self-conditioning, vision tower: fp16 passthrough
23 shards, ~26 GB on disk, peak runtime RSS ≈ 23.8 GB (M5 Max)

Capabilities


Text generation	✅ block diffusion (~28–42 tok/s @ 48 steps (often converges in fewer steps than MXFP4), M5 Max)
Vision (single/multi image)	✅ Gemma-4 unified vision tower, 280 soft tokens/image
Tool calling	✅ Gemma-4 format `<\|tool_call>call:name{...}<tool_call\|>`
Reasoning channel	✅ harmony `<\|channel>thought…<channel\|>`
Audio	❌ not in this checkpoint (no audio_config)
Video	❌ no `video_token_id`

Generation contract

All diffusion sampling parameters live in generation_config.json and are honored by the runtime: max_denoising_steps=48, entropy bound 0.1, temperature schedule 0.8→0.4, stability 1, confidence 0.005, eos_token_id=[1, 106, 50], pad 0. Wire temperature/top_p are ignored by design — the denoising schedule is bundle-owned. Speed/quality is controlled by the denoising-step budget (Osaurus exposes this as a server setting, default 16 ≈ 2× faster than the bundle default and verified coherent; below 12 quality degrades).

The chat template (chat_template.jinja) ships in this repo, including tool-call and thinking-channel rendering.

Known behavior

Very terse prompts under greedy denoising can occasionally converge to an empty (EOS-first) canvas — inherent to the reference sampling algorithm with random canvas initialization; retry or rephrase.