Libraries MLX How to use shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-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("shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit")
config = load_config("shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-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) Transformers How to use shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit")
messages = [
{
"role": "user",
"content": [
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
{"type": "text", "text": "What animal is on the candy?"}
]
},
]
pipe(text=messages) # Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM
processor = AutoProcessor.from_pretrained("shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit")
model = AutoModelForMultimodalLM.from_pretrained("shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit", device_map="auto")
messages = [
{
"role": "user",
"content": [
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
{"type": "text", "text": "What animal is on the candy?"}
]
},
]
inputs = processor.apply_chat_template(
messages,
add_generation_prompt=True,
tokenize=True,
return_dict=True,
return_tensors="pt",
).to(model.device)
outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) Notebooks Google Colab Kaggle Local Apps Settings LM Studio vLLM How to use shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit with vLLM:
Install from pip and serve model # Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Describe this image in one sentence."
},
{
"type": "image_url",
"image_url": {
"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
}
}
]
}
]
}' Use Docker docker model run hf.co/shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit SGLang How to use shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit with SGLang:
Install from pip and serve model # Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit" \
--host 0.0.0.0 \
--port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Describe this image in one sentence."
},
{
"type": "image_url",
"image_url": {
"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
}
}
]
}
]
}' Use Docker images docker run --gpus all \
--shm-size 32g \
-p 30000:30000 \
-v ~/.cache/huggingface:/root/.cache/huggingface \
--env "HF_TOKEN=<secret>" \
--ipc=host \
lmsysorg/sglang:latest \
python3 -m sglang.launch_server \
--model-path "shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit" \
--host 0.0.0.0 \
--port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Describe this image in one sentence."
},
{
"type": "image_url",
"image_url": {
"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
}
}
]
}
]
}' Unsloth Desktop Pi How to use shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-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 "shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-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": "shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit"
}
]
}
}
} Run Pi # Start Pi in your project directory:
pi Docker Model Runner How to use shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit with Docker Model Runner:
docker model run hf.co/shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit Hermes Agent How to use shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-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 "shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-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 shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit Run Hermes hermes Atomic Chat OpenClaw How to use shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-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 "shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-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 "shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-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" 
# 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("shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit") config = load_config("shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-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)