Instructions to use LiquidAI/d1-2B-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LiquidAI/d1-2B-MLX-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("LiquidAI/d1-2B-MLX-8bit")
config = load_config("LiquidAI/d1-2B-MLX-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 LiquidAI/d1-2B-MLX-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 "LiquidAI/d1-2B-MLX-8bit"

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": "LiquidAI/d1-2B-MLX-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use LiquidAI/d1-2B-MLX-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 "LiquidAI/d1-2B-MLX-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 LiquidAI/d1-2B-MLX-8bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use LiquidAI/d1-2B-MLX-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 "LiquidAI/d1-2B-MLX-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 "LiquidAI/d1-2B-MLX-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"

d1-2B-MLX-8bit / config.json

mlabonne

ykhrustalev

d1-2B-MLX-8bit

4977063 about 5 hours ago

Raw History Blame Contribute Delete

3.65 kB

{
    "architectures": [
        "D1Model"
    ],
    "auto_map": {
        "AutoModel": "modeling_d1_lfm3_vl.D1Model",
        "AutoConfig": "native_lfm3_vl.Lfm3VlConfig"
    },
    "bos_token_id": 124894,
    "d1_attention": "set",
    "d1_codes": 2,
    "d1_numbers": true,
    "d1_set_size": 16,
    "d1_vision_max_pixels": 1638400,
    "downsample_factor": 2,
    "dtype": "float16",
    "eos_token_id": 124900,
    "image_token_id": 125030,
    "model_type": "lfm3_vl",
    "pad_token_id": 124893,
    "projector_bias": true,
    "projector_hidden_act": "gelu",
    "projector_hidden_size": 4096,
    "projector_layer_norm_eps": 1e-06,
    "quantization": {
        "group_size": 64,
        "bits": 8,
        "mode": "affine"
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 8,
        "mode": "affine"
    },
    "text_config": {
        "bos_token_id": 124894,
        "conv_L_cache": 7,
        "conv_bias": false,
        "dtype": "float16",
        "eos_token_id": 124900,
        "head_dim": 128,
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 7680,
        "layer_types": [
            "conv",
            "conv",
            "full_attention",
            "conv",
            "sliding_attention",
            "conv",
            "full_attention",
            "conv",
            "sliding_attention",
            "conv",
            "full_attention",
            "conv",
            "sliding_attention",
            "conv",
            "full_attention",
            "conv",
            "sliding_attention",
            "conv",
            "full_attention",
            "conv",
            "sliding_attention",
            "conv",
            "full_attention",
            "conv"
        ],
        "max_position_embeddings": 128000,
        "model_type": "lfm3",
        "norm_eps": 1e-05,
        "num_attention_heads": 16,
        "num_hidden_layers": 24,
        "num_key_value_heads": 4,
        "pad_token_id": 124893,
        "rope_parameters": {
            "full_attention": {
                "partial_rotary_factor": 0.5,
                "rope_theta": 1000000.0,
                "rope_type": "default"
            },
            "sliding_attention": {
                "rope_theta": 10000,
                "rope_type": "default"
            }
        },
        "sliding_window": 256,
        "tie_word_embeddings": true,
        "use_cache": true,
        "use_sandwich_norm": true,
        "vocab_size": 128000
    },
    "tie_word_embeddings": true,
    "transformers_version": "5.19.0",
    "video_token_id": 125029,
    "vision_config": {
        "conv_kernel_size": 3,
        "dtype": "float16",
        "hidden_size": 1024,
        "in_channels": 3,
        "initializer_range": 0.02,
        "intermediate_size": 2560,
        "layer_types": [
            "conv",
            "conv",
            "full_attention",
            "conv",
            "full_attention",
            "conv",
            "full_attention",
            "conv",
            "full_attention",
            "conv",
            "full_attention",
            "conv",
            "full_attention",
            "conv"
        ],
        "model_type": "lfm3_vl_vision",
        "norm_eps": 1e-05,
        "num_attention_heads": 16,
        "num_hidden_layers": 14,
        "num_key_value_heads": 8,
        "patch_size": 16,
        "rope_parameters": {
            "rope_theta": 1000000.0,
            "rope_type": "axial"
        },
        "spatial_merge_size": 2,
        "temporal_patch_size": 2
    },
    "vision_end_token_id": 125010,
    "vision_start_token_id": 125009
}

	{
	"architectures": [
	"D1Model"
	],
	"auto_map": {
	"AutoModel": "modeling_d1_lfm3_vl.D1Model",
	"AutoConfig": "native_lfm3_vl.Lfm3VlConfig"
	},
	"bos_token_id": 124894,
	"d1_attention": "set",
	"d1_codes": 2,
	"d1_numbers": true,
	"d1_set_size": 16,
	"d1_vision_max_pixels": 1638400,
	"downsample_factor": 2,
	"dtype": "float16",
	"eos_token_id": 124900,
	"image_token_id": 125030,
	"model_type": "lfm3_vl",
	"pad_token_id": 124893,
	"projector_bias": true,
	"projector_hidden_act": "gelu",
	"projector_hidden_size": 4096,
	"projector_layer_norm_eps": 1e-06,
	"quantization": {
	"group_size": 64,
	"bits": 8,
	"mode": "affine"
	},
	"quantization_config": {
	"group_size": 64,
	"bits": 8,
	"mode": "affine"
	},
	"text_config": {
	"bos_token_id": 124894,
	"conv_L_cache": 7,
	"conv_bias": false,
	"dtype": "float16",
	"eos_token_id": 124900,
	"head_dim": 128,
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"intermediate_size": 7680,
	"layer_types": [
	"conv",
	"conv",
	"full_attention",
	"conv",
	"sliding_attention",
	"conv",
	"full_attention",
	"conv",
	"sliding_attention",
	"conv",
	"full_attention",
	"conv",
	"sliding_attention",
	"conv",
	"full_attention",
	"conv",
	"sliding_attention",
	"conv",
	"full_attention",
	"conv",
	"sliding_attention",
	"conv",
	"full_attention",
	"conv"
	],
	"max_position_embeddings": 128000,
	"model_type": "lfm3",
	"norm_eps": 1e-05,
	"num_attention_heads": 16,
	"num_hidden_layers": 24,
	"num_key_value_heads": 4,
	"pad_token_id": 124893,
	"rope_parameters": {
	"full_attention": {
	"partial_rotary_factor": 0.5,
	"rope_theta": 1000000.0,
	"rope_type": "default"
	},
	"sliding_attention": {
	"rope_theta": 10000,
	"rope_type": "default"
	}
	},
	"sliding_window": 256,
	"tie_word_embeddings": true,
	"use_cache": true,
	"use_sandwich_norm": true,
	"vocab_size": 128000
	},
	"tie_word_embeddings": true,
	"transformers_version": "5.19.0",
	"video_token_id": 125029,
	"vision_config": {
	"conv_kernel_size": 3,
	"dtype": "float16",
	"hidden_size": 1024,
	"in_channels": 3,
	"initializer_range": 0.02,
	"intermediate_size": 2560,
	"layer_types": [
	"conv",
	"conv",
	"full_attention",
	"conv",
	"full_attention",
	"conv",
	"full_attention",
	"conv",
	"full_attention",
	"conv",
	"full_attention",
	"conv",
	"full_attention",
	"conv"
	],
	"model_type": "lfm3_vl_vision",
	"norm_eps": 1e-05,
	"num_attention_heads": 16,
	"num_hidden_layers": 14,
	"num_key_value_heads": 8,
	"patch_size": 16,
	"rope_parameters": {
	"rope_theta": 1000000.0,
	"rope_type": "axial"
	},
	"spatial_merge_size": 2,
	"temporal_patch_size": 2
	},
	"vision_end_token_id": 125010,
	"vision_start_token_id": 125009
	}