Instructions to use inferencerlabs/granite-vision-4.1-4b-MLX-Q9 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inferencerlabs/granite-vision-4.1-4b-MLX-Q9 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("inferencerlabs/granite-vision-4.1-4b-MLX-Q9")
config = load_config("inferencerlabs/granite-vision-4.1-4b-MLX-Q9")

# 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 inferencerlabs/granite-vision-4.1-4b-MLX-Q9 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "inferencerlabs/granite-vision-4.1-4b-MLX-Q9"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "inferencerlabs/granite-vision-4.1-4b-MLX-Q9"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use inferencerlabs/granite-vision-4.1-4b-MLX-Q9 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 "inferencerlabs/granite-vision-4.1-4b-MLX-Q9"

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 inferencerlabs/granite-vision-4.1-4b-MLX-Q9

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use inferencerlabs/granite-vision-4.1-4b-MLX-Q9 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "inferencerlabs/granite-vision-4.1-4b-MLX-Q9"

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 "inferencerlabs/granite-vision-4.1-4b-MLX-Q9" \
  --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"

inferencerlabs commited on May 27

Commit

6bf0c83

verified ·

1 Parent(s): 56205d8

Upload model file

Browse files

Files changed (1) hide show

config.json +210 -0

config.json ADDED Viewed

	@@ -0,0 +1,210 @@

+{
+    "architectures": [
+        "Granite4VisionForConditionalGeneration"
+    ],
+    "auto_map": {
+        "AutoConfig": "configuration.Granite4VisionConfig",
+        "AutoModel": "modeling.Granite4VisionForConditionalGeneration",
+        "AutoModelForVision2Seq": "modeling.Granite4VisionForConditionalGeneration",
+        "AutoModelForImageTextToText": "modeling.Granite4VisionForConditionalGeneration",
+        "AutoProcessor": "processing.Granite4VisionProcessor"
+    },
+    "deepstack_layer_map": [
+        [
+            -19,
+            9
+        ],
+        [
+            -13,
+            6
+        ],
+        [
+            -7,
+            3
+        ],
+        [
+            -1,
+            0
+        ]
+    ],
+    "downsample_rate": "4/8",
+    "dtype": "bfloat16",
+    "eos_token_id": 100257,
+    "image_grid_pinpoints": [
+        [
+            384,
+            384
+        ],
+        [
+            384,
+            768
+        ],
+        [
+            384,
+            1152
+        ],
+        [
+            384,
+            1536
+        ],
+        [
+            384,
+            1920
+        ],
+        [
+            384,
+            2304
+        ],
+        [
+            384,
+            2688
+        ],
+        [
+            384,
+            3072
+        ],
+        [
+            384,
+            3456
+        ],
+        [
+            384,
+            3840
+        ],
+        [
+            768,
+            384
+        ],
+        [
+            768,
+            768
+        ],
+        [
+            768,
+            1152
+        ],
+        [
+            768,
+            1536
+        ],
+        [
+            768,
+            1920
+        ],
+        [
+            1152,
+            384
+        ],
+        [
+            1152,
+            768
+        ],
+        [
+            1152,
+            1152
+        ],
+        [
+            1536,
+            384
+        ],
+        [
+            1536,
+            768
+        ],
+        [
+            1920,
+            384
+        ],
+        [
+            1920,
+            768
+        ],
+        [
+            2304,
+            384
+        ],
+        [
+            2688,
+            384
+        ],
+        [
+            3072,
+            384
+        ],
+        [
+            3456,
+            384
+        ],
+        [
+            3840,
+            384
+        ]
+    ],
+    "image_seq_length": 576,
+    "image_token_index": 100352,
+    "initializer_range": 0.02,
+    "model_type": "granite4_vision",
+    "projector_dropout": 0.1,
+    "projector_hidden_act": "gelu",
+    "quantization_config": {
+        "group_size": 32
+    },
+    "spatial_stride": 2,
+    "spatial_target_layers": [
+        12,
+        15,
+        18,
+        21
+    ],
+    "spatial_vision_layer": -1,
+    "text_config": {
+        "architectures": [
+            "GraniteForCausalLM"
+        ],
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "attention_multiplier": 0.015625,
+        "bos_token_id": 100257,
+        "embedding_multiplier": 12.0,
+        "eos_token_id": 100257,
+        "hidden_act": "silu",
+        "hidden_size": 2560,
+        "initializer_range": 0.1,
+        "intermediate_size": 8192,
+        "logits_scaling": 10.0,
+        "max_position_embeddings": 131072,
+        "mlp_bias": false,
+        "model_type": "granite",
+        "num_attention_heads": 40,
+        "num_hidden_layers": 40,
+        "num_key_value_heads": 8,
+        "pad_token_id": 100256,
+        "residual_multiplier": 0.22,
+        "rms_norm_eps": 1e-05,
+        "rope_scaling": null,
+        "rope_theta": 10000000,
+        "tie_word_embeddings": true,
+        "torch_dtype": "bfloat16",
+        "transformers_version": "4.53.3",
+        "use_cache": true,
+        "vocab_size": 100353
+    },
+    "tie_word_embeddings": true,
+    "transformers_version": "4.57.3",
+    "use_image_newline_parameter": true,
+    "use_spatial_sampling": true,
+    "vision_config": {
+        "attention_dropout": 0.0,
+        "hidden_act": "gelu_pytorch_tanh",
+        "hidden_size": 1152,
+        "image_size": 384,
+        "intermediate_size": 4304,
+        "layer_norm_eps": 1e-06,
+        "model_type": "siglip_vision_model",
+        "num_attention_heads": 16,
+        "num_channels": 3,
+        "num_hidden_layers": 27,
+        "patch_size": 16
+    },
+    "vision_feature_select_strategy": "full"
+}