Instructions to use mlx-community/gemma-4-12B-it-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/gemma-4-12B-it-8bit 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("mlx-community/gemma-4-12B-it-8bit")
config = load_config("mlx-community/gemma-4-12B-it-8bit")

# 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 mlx-community/gemma-4-12B-it-8bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/gemma-4-12B-it-8bit"

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": "mlx-community/gemma-4-12B-it-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlx-community/gemma-4-12B-it-8bit 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 "mlx-community/gemma-4-12B-it-8bit"

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 mlx-community/gemma-4-12B-it-8bit

Run Hermes

hermes

OpenClaw new

How to use mlx-community/gemma-4-12B-it-8bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/gemma-4-12B-it-8bit"

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 "mlx-community/gemma-4-12B-it-8bit" \
  --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"

pcuenq HF Staff commited on Jun 8

Commit

200bb6d

1 Parent(s): bceca1e

Update checkpoint (#3)

Browse files

- Update checkpoint (235d66baf459abe4206164ba52c1f092827e6b8c)

Files changed (2) hide show

README.md +1 -1
config.json +3 -1155

README.md CHANGED Viewed

@@ -1,7 +1,7 @@
 ---
 language: en
-library_name: mlx
 pipeline_tag: image-text-to-text
 tags:
 - mlx
 ---

 ---
 language: en
 pipeline_tag: image-text-to-text
+library_name: mlx
 tags:
 - mlx
 ---

config.json CHANGED Viewed

@@ -45,1164 +45,12 @@
     "quantization": {
         "group_size": 64,
         "bits": 8,
-        "mode": "affine",
-        "language_model.model.layers.0.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.0.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.0.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.1.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.1.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.1.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.2.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.2.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.2.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.3.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.3.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.3.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.4.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.4.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.4.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.5.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.5.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.5.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.6.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.6.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.6.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.7.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.7.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.7.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.8.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.8.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.8.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.9.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.9.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.9.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.10.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.10.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.10.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.11.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.11.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.11.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.12.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.12.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.12.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.13.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.13.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.13.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.14.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.14.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.14.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.15.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.15.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.15.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.16.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.16.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.16.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.17.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.17.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.17.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.18.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.18.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.18.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.19.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.19.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.19.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.20.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.20.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.20.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.21.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.21.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.21.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.22.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.22.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.22.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.23.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.23.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.23.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.24.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.24.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.24.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.25.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.25.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.25.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.26.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.26.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.26.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.27.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.27.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.27.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.28.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.28.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.28.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.29.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.29.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.29.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.30.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.30.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.30.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.31.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.31.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.31.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.32.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.32.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.32.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.33.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.33.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.33.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.34.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.34.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.34.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.35.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.35.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.35.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.36.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.36.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.36.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.37.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.37.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.37.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.38.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.38.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.38.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.39.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.39.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.39.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.40.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.40.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.40.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.41.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.41.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.41.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.42.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.42.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.42.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.43.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.43.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.43.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.44.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.44.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.44.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.45.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.45.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.45.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.46.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.46.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.46.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.47.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.47.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.47.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        }
     },
     "quantization_config": {
         "group_size": 64,
         "bits": 8,
-        "mode": "affine",
-        "language_model.model.layers.0.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.0.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.0.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.1.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.1.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.1.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.2.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.2.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.2.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.3.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.3.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.3.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.4.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.4.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.4.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.5.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.5.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.5.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.6.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.6.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.6.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.7.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.7.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.7.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.8.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.8.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.8.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.9.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.9.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.9.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.10.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.10.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.10.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.11.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.11.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.11.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.12.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.12.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.12.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.13.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.13.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.13.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.14.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.14.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.14.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.15.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.15.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.15.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.16.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.16.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.16.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.17.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.17.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.17.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.18.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.18.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.18.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.19.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.19.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.19.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.20.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.20.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.20.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.21.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.21.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.21.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.22.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.22.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.22.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.23.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.23.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.23.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.24.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.24.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.24.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.25.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.25.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.25.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.26.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.26.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.26.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.27.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.27.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.27.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.28.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.28.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.28.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.29.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.29.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.29.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.30.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.30.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.30.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.31.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.31.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.31.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.32.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.32.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.32.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.33.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.33.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.33.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.34.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.34.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.34.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.35.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.35.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.35.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.36.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.36.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.36.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.37.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.37.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.37.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.38.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.38.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.38.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.39.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.39.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.39.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.40.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.40.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.40.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.41.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.41.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.41.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.42.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.42.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.42.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.43.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.43.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.43.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.44.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.44.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.44.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.45.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.45.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.45.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.46.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.46.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.46.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.47.mlp.gate_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.47.mlp.down_proj": {
-            "group_size": 64,
-            "bits": 8
-        },
-        "language_model.model.layers.47.mlp.up_proj": {
-            "group_size": 64,
-            "bits": 8
-        }
     },
     "text_config": {
         "attention_bias": false,
@@ -1269,7 +117,7 @@
             "sliding_attention",
             "full_attention"
         ],
-        "max_position_embeddings": 131072,
         "model_type": "gemma4_unified_text",
         "moe_intermediate_size": null,
         "num_attention_heads": 16,

     "quantization": {
         "group_size": 64,
         "bits": 8,
+        "mode": "affine"
     },
     "quantization_config": {
         "group_size": 64,
         "bits": 8,
+        "mode": "affine"
     },
     "text_config": {
         "attention_bias": false,
             "sliding_attention",
             "full_attention"
         ],
+        "max_position_embeddings": 262144,
         "model_type": "gemma4_unified_text",
         "moe_intermediate_size": null,
         "num_attention_heads": 16,