Instructions to use hermitdave/BigBang-v1-MLX-VLM-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hermitdave/BigBang-v1-MLX-VLM-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("hermitdave/BigBang-v1-MLX-VLM-4bit")
config = load_config("hermitdave/BigBang-v1-MLX-VLM-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 hermitdave/BigBang-v1-MLX-VLM-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 "hermitdave/BigBang-v1-MLX-VLM-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": "hermitdave/BigBang-v1-MLX-VLM-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use hermitdave/BigBang-v1-MLX-VLM-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 "hermitdave/BigBang-v1-MLX-VLM-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 hermitdave/BigBang-v1-MLX-VLM-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use hermitdave/BigBang-v1-MLX-VLM-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 "hermitdave/BigBang-v1-MLX-VLM-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 "hermitdave/BigBang-v1-MLX-VLM-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"

BigBang-v1-MLX-VLM-4bit

This model was converted to MLX format from endless-frontier/BigBang-v1 using mlx_vlm version 0.6.17.

Quantization: Uniform 4-bit, group size 64.

Use with mlx-vlm

from mlx_vlm import load, generate

model, processor = load("mlx-community/BigBang-v1-MLX-VLM-4bit")

messages = [
    {"role": "user", "content": [
        {"type": "text", "text": "Describe this image."},
        {"type": "image", "image": "path/to/image.jpg"},
    ]}
]
prompt = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
result = generate(model, processor, prompt=prompt, max_tokens=512)
print(result.text if hasattr(result, 'text') else result)

Model Info

Architecture: qwen3_5_moe — 35B total, 3B active, 256 experts (8/tok)
Attention: Hybrid linear + full attention
Context: 262K tokens
Type: Multimodal (language + vision encoder)
Vision: Qwen3.5 MoE ViT (patch 16, 27 layers, hidden 1152)

Variants

Repo	Quantization	Size	Use Case
BigBang-v1-MLX-4bit	uniform 4-bit	~19.5 GB	Text-only, fast
BigBang-v1-MLX-Q4_K_M	mixed_4_6	~21.0 GB	Text-only, quality
BigBang-v1-MLX-VLM-4bit	uniform 4-bit	~20.4 GB	Multimodal, fast
BigBang-v1-MLX-VLM-Q4_K_M	mixed_4_6	~22.0 GB	Multimodal, quality