Instructions to use meossistant/clef-flash-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meossistant/clef-flash-4bit with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="meossistant/clef-flash-4bit")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("meossistant/clef-flash-4bit")
model = AutoModelForMultimodalLM.from_pretrained("meossistant/clef-flash-4bit", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use meossistant/clef-flash-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meossistant/clef-flash-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meossistant/clef-flash-4bit",
		"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/meossistant/clef-flash-4bit

SGLang

How to use meossistant/clef-flash-4bit 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 "meossistant/clef-flash-4bit" \
    --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": "meossistant/clef-flash-4bit",
		"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 "meossistant/clef-flash-4bit" \
        --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": "meossistant/clef-flash-4bit",
		"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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use meossistant/clef-flash-4bit with Docker Model Runner:
```
docker model run hf.co/meossistant/clef-flash-4bit
```

clef-flash-4bit

File size: 1,994 Bytes

3b2c496

---
license: apache-2.0
library_name: transformers
pipeline_tag: image-text-to-text
base_model: Cloudflare/clef-flash
base_model_relation: quantized
tags:
- clef
- cloudflare
- systemone
- qwen3.5
- post-train
- image-text-to-typed-output
- multimodal
- structured-output
- classification
- custom-code
- bitsandbytes
- 4-bit
- nf4
---

# Clef-Flash (4-bit NF4 Quantized)

This repository contains the **4-bit NF4 quantized** version of Cloudflare's **Clef-Flash** multimodal decision model.

- **Base Model:** [Cloudflare/clef-flash](https://huggingface.co/Cloudflare/clef-flash)
- **Quantization:** 4-bit NormalFloat (NF4) with double quantization via `bitsandbytes`
- **Compute Dtype:** `bfloat16`
- **Backbone:** Qwen3.5-9B
- **Joint Schema Head:** Unquantized BF16 precision for accurate scoring and routing
- **Format:** Safetensors

## Quickstart / Usage

```python
import sys
import torch
from huggingface_hub import snapshot_download

path = snapshot_download("meossistant/clef-flash-4bit")
sys.path.insert(0, path)
from joint_schema_model import load_release_model, systemone

model, processor = load_release_model(path, device="cuda")

response = systemone(model, processor, {
    "model": "clef-flash",
    "state": "Our checkout started returning errors and orders are blocked.",
    "questions": {
        "department": {
            "type": "choice",
            "instructions": "Which team should handle the message?",
            "criteria": {"billing": "Payments or invoices", "technical": "Bugs or outages"},
        },
        "urgency": {"type": "score", "criteria": ["Can wait", "This week", "Today"]},
        "outage": {"type": "noul", "instructions": "Is a service down?"},
    },
})
print(response["answers"])
```

## Overview

Clef-Flash is a 9B multimodal model that turns a state and a schema of typed questions into decisions in a single forward pass.
This 4-bit quantized version reduces the VRAM requirement to ~6 GB, making it easily runnable on consumer GPUs.