Instructions to use zecanard/gemma-4-31B-it-uncensored-abliterix-MLX-2bit-mixed_2_6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zecanard/gemma-4-31B-it-uncensored-abliterix-MLX-2bit-mixed_2_6 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("zecanard/gemma-4-31B-it-uncensored-abliterix-MLX-2bit-mixed_2_6")
config = load_config("zecanard/gemma-4-31B-it-uncensored-abliterix-MLX-2bit-mixed_2_6")

# 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 zecanard/gemma-4-31B-it-uncensored-abliterix-MLX-2bit-mixed_2_6 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "zecanard/gemma-4-31B-it-uncensored-abliterix-MLX-2bit-mixed_2_6"

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": "zecanard/gemma-4-31B-it-uncensored-abliterix-MLX-2bit-mixed_2_6"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use zecanard/gemma-4-31B-it-uncensored-abliterix-MLX-2bit-mixed_2_6 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 "zecanard/gemma-4-31B-it-uncensored-abliterix-MLX-2bit-mixed_2_6"

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 zecanard/gemma-4-31B-it-uncensored-abliterix-MLX-2bit-mixed_2_6

Run Hermes

hermes

OpenClaw new

How to use zecanard/gemma-4-31B-it-uncensored-abliterix-MLX-2bit-mixed_2_6 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "zecanard/gemma-4-31B-it-uncensored-abliterix-MLX-2bit-mixed_2_6"

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 "zecanard/gemma-4-31B-it-uncensored-abliterix-MLX-2bit-mixed_2_6" \
  --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"

zecanard commited on May 8

Commit

f6de81c

verified ·

1 Parent(s): 6e012c5

Add files using upload-large-folder tool

Browse files

Files changed (2) hide show

README.md +1 -1
processor_config.json +12 -2

README.md CHANGED Viewed

@@ -18,7 +18,7 @@ tags:
 ---
 # 🦆 zecanard/gemma-4-31B-it-uncensored-abliterix-MLX-2bit-mixed_2_6
-[This model](https://huggingface.co/zecanard/gemma-4-31B-it-uncensored-abliterix-MLX-2bit-mixed_2_6) was converted to MLX from [`wangzhang/gemma-4-31B-it-abliterated`](https://huggingface.co/wangzhang/gemma-4-31B-it-abliterated) using `mlx-vlm` version **0.4.4**.
 Please refer to the [original model card](https://huggingface.co/wangzhang/gemma-4-31B-it-abliterated) for more details.
 ## 🌟 Quality

 ---
 # 🦆 zecanard/gemma-4-31B-it-uncensored-abliterix-MLX-2bit-mixed_2_6
+[This model](https://huggingface.co/zecanard/gemma-4-31B-it-uncensored-abliterix-MLX-2bit-mixed_2_6) was converted to MLX from [`wangzhang/gemma-4-31B-it-abliterated`](https://huggingface.co/wangzhang/gemma-4-31B-it-abliterated) using `mlx-vlm` version **0.5.0**.
 Please refer to the [original model card](https://huggingface.co/wangzhang/gemma-4-31B-it-abliterated) for more details.
 ## 🌟 Quality

processor_config.json CHANGED Viewed

@@ -27,5 +27,15 @@
     }
   },
   "image_seq_length": 280,
-  "processor_class": "Gemma4Processor"
-}

     }
   },
   "image_seq_length": 280,
+  "processor_class": "Gemma4Processor",
+  "feature_extractor": {
+    "feature_extractor_type": "Gemma4AudioFeatureExtractor",
+    "sampling_rate": 16000,
+    "num_mel_filters": 128,
+    "fft_length": 512,
+    "hop_length": 160,
+    "chunk_duration": 8.0,
+    "overlap_duration": 1.0
+  },
+  "audio_ms_per_token": 40
+}