Instructions to use ServiceNow-AI/Apriel-1.6-15b-Thinker with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ServiceNow-AI/Apriel-1.6-15b-Thinker with Transformers:

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

pipe = pipeline("image-text-to-text", model="ServiceNow-AI/Apriel-1.6-15b-Thinker")
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("ServiceNow-AI/Apriel-1.6-15b-Thinker")
model = AutoModelForMultimodalLM.from_pretrained("ServiceNow-AI/Apriel-1.6-15b-Thinker", 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 ServiceNow-AI/Apriel-1.6-15b-Thinker with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ServiceNow-AI/Apriel-1.6-15b-Thinker"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ServiceNow-AI/Apriel-1.6-15b-Thinker",
		"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/ServiceNow-AI/Apriel-1.6-15b-Thinker

SGLang

How to use ServiceNow-AI/Apriel-1.6-15b-Thinker 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 "ServiceNow-AI/Apriel-1.6-15b-Thinker" \
    --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": "ServiceNow-AI/Apriel-1.6-15b-Thinker",
		"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 "ServiceNow-AI/Apriel-1.6-15b-Thinker" \
        --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": "ServiceNow-AI/Apriel-1.6-15b-Thinker",
		"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 ServiceNow-AI/Apriel-1.6-15b-Thinker with Docker Model Runner:
```
docker model run hf.co/ServiceNow-AI/Apriel-1.6-15b-Thinker
```

Added Average score for text benchmark

by davasam - opened Dec 9, 2025

base: refs/heads/main

←

from: refs/pr/4

Discussion Files changed

+22

-7

Files changed (1) hide show

README.md +22 -7

README.md CHANGED Viewed

@@ -62,7 +62,18 @@ Please see our [blog post](https://huggingface.co/blog/ServiceNow-AI/apriel-1p6-
       <th>Claude 4.5 Sonnet (thinking)</th>
       <th>o3-mini (high)</th>
     </tr>
     <!-- Function Calling -->
     <tr>
       <td rowspan="5" class="category">Function Calling</td>
@@ -199,7 +210,7 @@ Please see our [blog post](https://huggingface.co/blog/ServiceNow-AI/apriel-1p6-
       <td>LCB</td>
       <td>81</td>
       <td>73</td>
-      <td>65</td>
       <td>77</td>
       <td>70</td>
       <td>84</td>
@@ -210,7 +221,7 @@ Please see our [blog post](https://huggingface.co/blog/ServiceNow-AI/apriel-1p6-
       <td>SciCode</td>
       <td>37</td>
       <td>35</td>
-      <td>36</td>
       <td>40</td>
       <td>41</td>
       <td>39</td>
@@ -244,7 +255,7 @@ Please see our [blog post](https://huggingface.co/blog/ServiceNow-AI/apriel-1p6-
     </tr>
     <tr>
       <td>Work-Arena L1</td>
-      <td>58</td>
       <td>51.5</td>
       <td>50.9</td>
       <td>63.9</td>
@@ -304,7 +315,7 @@ Please see our [blog post](https://huggingface.co/blog/ServiceNow-AI/apriel-1p6-
       <td>MMLU Pro</td>
       <td>79</td>
       <td>77</td>
-      <td>85</td>
       <td>85</td>
       <td>83</td>
       <td>84</td>
@@ -362,13 +373,17 @@ Please see our [blog post](https://huggingface.co/blog/ServiceNow-AI/apriel-1p6-
       <td>62</td>
       <td>68</td>
       <td>66</td>
-      <td>-</td>
     </tr>
   </table>
-\* AA LCR score in the table is with [DCA](https://arxiv.org/pdf/2402.17463) enabled. With default config, the model scores 36 on AA LCR.
 ---

       <th>Claude 4.5 Sonnet (thinking)</th>
       <th>o3-mini (high)</th>
     </tr>
+    <tr>
+      <td></td>
+      <td>Average Score**</td>
+      <td>53.22</td>
+      <td>46.56</td>
+      <td>52.56</td>
+      <td>51.92</td>
+      <td>50.71</td>
+      <td>62.58</td>
+      <td>60.37</td>
+      <td>48.85</td>
+    </tr>
     <!-- Function Calling -->
     <tr>
       <td rowspan="5" class="category">Function Calling</td>
       <td>LCB</td>
       <td>81</td>
       <td>73</td>
+      <td>88</td>
       <td>77</td>
       <td>70</td>
       <td>84</td>
       <td>SciCode</td>
       <td>37</td>
       <td>35</td>
+      <td>39</td>
       <td>40</td>
       <td>41</td>
       <td>39</td>
     </tr>
     <tr>
       <td>Work-Arena L1</td>
+      <td>50.2</td>
       <td>51.5</td>
       <td>50.9</td>
       <td>63.9</td>
       <td>MMLU Pro</td>
       <td>79</td>
       <td>77</td>
+      <td>81</td>
       <td>85</td>
       <td>83</td>
       <td>84</td>
       <td>62</td>
       <td>68</td>
       <td>66</td>
+      <td>30***</td>
     </tr>
   </table>
+\* This score is with [DCA](https://arxiv.org/pdf/2402.17463) enabled. Without this, the model scores 36.
+\** The average score is calculated using all benchmarks except BFCL v3 Only and DeepResearchBench, since some models do not have scores for these two benchmarks.
+\*** AA LCR score for o3-mini-high is projected score based on its AA Index score.
 ---