Instructions to use spiderversekid/LFM3-Omni-2B-Uncensored-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use spiderversekid/LFM3-Omni-2B-Uncensored-MLX-4bit 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("spiderversekid/LFM3-Omni-2B-Uncensored-MLX-4bit")
config = load_config("spiderversekid/LFM3-Omni-2B-Uncensored-MLX-4bit")

# 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 spiderversekid/LFM3-Omni-2B-Uncensored-MLX-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "spiderversekid/LFM3-Omni-2B-Uncensored-MLX-4bit"

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": "spiderversekid/LFM3-Omni-2B-Uncensored-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use spiderversekid/LFM3-Omni-2B-Uncensored-MLX-4bit 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 "spiderversekid/LFM3-Omni-2B-Uncensored-MLX-4bit"

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 spiderversekid/LFM3-Omni-2B-Uncensored-MLX-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use spiderversekid/LFM3-Omni-2B-Uncensored-MLX-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "spiderversekid/LFM3-Omni-2B-Uncensored-MLX-4bit"

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 "spiderversekid/LFM3-Omni-2B-Uncensored-MLX-4bit" \
  --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"

LFM3-Omni-2B-Uncensored-MLX-4bit

High-quality 4-bit MLX conversion of OpenIntelligenceNet/LFM3-Omni-2B-Uncensored for Apple Silicon, built with mlx-vlm (0.7.11) and verified for out-of-the-box compatibility with Osaurus (vmlx) and mlx-vlm.

8-bit sibling repo: spiderversekid/LFM3-Omni-2B-Uncensored-MLX-8bit

Conversion & Quantization Details

Language Backbone (language_model): Preserves the original abliterated weights from OpenIntelligenceNet/LFM3-Omni-2B-Uncensored without re-abliteration:
- Decoder linear & short-conv projections: 4-bit affine (group_size=32)
- Tied embed_tokens / lm_head ([128000, 2048]): 6-bit affine (group_size=32) to preserve output logit fidelity (0.99755 logit cosine similarity vs. bfloat16)
- Attention head gates (self_attn.gate_proj, [16, 2048]): Full bfloat16 precision
Multimodal & Audio Modules (Full bfloat16 Precision):
- Vision Tower (vision_tower + multi_modal_projector)
- Audio Encoder (audio_tower + audio_projector)
- Audio Generation (depth_decoder + codebook_embedding)
- Liquid Audio Codec (audio_tokenizer/model.safetensors)

Usage

1. Osaurus (`vmlx`)

Import spiderversekid/LFM3-Omni-2B-Uncensored-MLX-4bit directly in Osaurus or place it in ~/MLXModels/spiderversekid/LFM3-Omni-2B-Uncensored-MLX-4bit.

2. `mlx-vlm` CLI

pip install -U mlx-vlm

Text-only generation:

python -m mlx_vlm.generate \
  --model spiderversekid/LFM3-Omni-2B-Uncensored-MLX-4bit \
  --prompt "Explain what a multimodal omni model can do." \
  --max-tokens 256 \
  --temperature 0.0

Image + Text generation:

python -m mlx_vlm.generate \
  --model spiderversekid/LFM3-Omni-2B-Uncensored-MLX-4bit \
  --image path/to/image.png \
  --prompt "Describe this image in detail." \
  --max-tokens 256 \
  --temperature 0.0

Downloads last month: 207

Safetensors

Model size

2B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for spiderversekid/LFM3-Omni-2B-Uncensored-MLX-4bit

Base model

LiquidAI/LFM3-Omni-2B

Finetuned

OpenIntelligenceNet/LFM3-Omni-2B-Uncensored

Quantized

(2)

this model

LFM3-Omni-2B-Uncensored-MLX-4bit

Conversion & Quantization Details

Usage

1. Osaurus (vmlx)

2. mlx-vlm CLI

Model tree for spiderversekid/LFM3-Omni-2B-Uncensored-MLX-4bit

1. Osaurus (`vmlx`)

2. `mlx-vlm` CLI