Instructions to use AITRADER/Huihui-Step3-VL-10B-abliterated-mlx-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AITRADER/Huihui-Step3-VL-10B-abliterated-mlx-fp16 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("AITRADER/Huihui-Step3-VL-10B-abliterated-mlx-fp16")
config = load_config("AITRADER/Huihui-Step3-VL-10B-abliterated-mlx-fp16")

# 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 AITRADER/Huihui-Step3-VL-10B-abliterated-mlx-fp16 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "AITRADER/Huihui-Step3-VL-10B-abliterated-mlx-fp16"

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": "AITRADER/Huihui-Step3-VL-10B-abliterated-mlx-fp16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use AITRADER/Huihui-Step3-VL-10B-abliterated-mlx-fp16 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 "AITRADER/Huihui-Step3-VL-10B-abliterated-mlx-fp16"

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 AITRADER/Huihui-Step3-VL-10B-abliterated-mlx-fp16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AITRADER/Huihui-Step3-VL-10B-abliterated-mlx-fp16 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "AITRADER/Huihui-Step3-VL-10B-abliterated-mlx-fp16"

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 "AITRADER/Huihui-Step3-VL-10B-abliterated-mlx-fp16" \
  --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"

Huihui-Step3-VL-10B-abliterated (MLX fp16)

MLX conversion (fp16) of huihui-ai/Huihui-Step3-VL-10B-abliterated.

Files

MLX weights: model-*.safetensors + model.safetensors.index.json
Loader code: step3_vl_mlx.py (referenced by config.json via model_file)

Text-Only Usage (mlx-lm)

This repo includes a minimal MLX module tree primarily meant for loading and quantization. Multimodal/image inference is not implemented in the included model file.

pip install -U mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("AITRADER/Huihui-Step3-VL-10B-abliterated-mlx-fp16")
print(generate(model, tokenizer, prompt="Hello!", max_tokens=128))

Source

Original model: huihui-ai/Huihui-Step3-VL-10B-abliterated

Downloads last month: 31

Safetensors

Model size

10B params

Tensor type

F16

MLX

Hardware compatibility

Quantized

Model tree for AITRADER/Huihui-Step3-VL-10B-abliterated-mlx-fp16

Base model

stepfun-ai/Step3-VL-10B-Base

Finetuned

stepfun-ai/Step3-VL-10B

Finetuned

huihui-ai/Huihui-Step3-VL-10B-abliterated

Finetuned

(1)

this model