Instructions to use nm-testing/pixtral-12b-FP8-dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nm-testing/pixtral-12b-FP8-dynamic with Transformers:

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

pipe = pipeline("image-text-to-text", model="nm-testing/pixtral-12b-FP8-dynamic")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("nm-testing/pixtral-12b-FP8-dynamic")
model = AutoModelForImageTextToText.from_pretrained("nm-testing/pixtral-12b-FP8-dynamic")
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

vLLM

How to use nm-testing/pixtral-12b-FP8-dynamic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nm-testing/pixtral-12b-FP8-dynamic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nm-testing/pixtral-12b-FP8-dynamic",
		"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/nm-testing/pixtral-12b-FP8-dynamic

SGLang

How to use nm-testing/pixtral-12b-FP8-dynamic 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 "nm-testing/pixtral-12b-FP8-dynamic" \
    --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": "nm-testing/pixtral-12b-FP8-dynamic",
		"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 "nm-testing/pixtral-12b-FP8-dynamic" \
        --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": "nm-testing/pixtral-12b-FP8-dynamic",
		"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 nm-testing/pixtral-12b-FP8-dynamic with Docker Model Runner:
```
docker model run hf.co/nm-testing/pixtral-12b-FP8-dynamic
```

shubhrapandit commited on Feb 25, 2025

Commit

82819f8

verified ·

1 Parent(s): 10cc40b

Update README.md

Browse files

Files changed (1) hide show

README.md +16 -8

README.md CHANGED Viewed

@@ -161,11 +161,11 @@ The following performance benchmarks were conducted with [vLLM](https://docs.vll
       <th>Model</th>
       <th>Average Cost Reduction</th>
       <th>Latency (s)</th>
-      <th>QPD</th>
-      <th>Latency (s)th>
-      <th>QPD</th>
       <th>Latency (s)</th>
-      <th>QPD</th>
     </tr>
   </thead>
   <tbody style="text-align: center">
@@ -265,7 +265,9 @@ The following performance benchmarks were conducted with [vLLM](https://docs.vll
   </tbody>
 </table>
 ### Multi-stream asynchronous performance (measured with vLLM version 0.7.2)
@@ -284,11 +286,11 @@ The following performance benchmarks were conducted with [vLLM](https://docs.vll
       <th>Model</th>
       <th>Average Cost Reduction</th>
       <th>Maximum throughput (QPS)</th>
-      <th>QPD</th>
       <th>Maximum throughput (QPS)</th>
-      <th>QPD</th>
       <th>Maximum throughput (QPS)</th>
-      <th>QPD</th>
     </tr>
   </thead>
   <tbody style="text-align: center">
@@ -386,4 +388,10 @@ The following performance benchmarks were conducted with [vLLM](https://docs.vll
       <td>6777</td>
     </tr>
   </tbody>
-</table>

       <th>Model</th>
       <th>Average Cost Reduction</th>
       <th>Latency (s)</th>
+      <th>Queries Per Dollar</th>
+      <th>Latency (s)<th>
+      <th>Queries Per Dollar</th>
       <th>Latency (s)</th>
+      <th>Queries Per Dollar</th>
     </tr>
   </thead>
   <tbody style="text-align: center">
   </tbody>
 </table>
+**Use case profiles: Image Size (WxH) / prompt tokens / generation tokens
+**QPD: Queries per dollar, based on on-demand cost at [Lambda Labs](https://lambdalabs.com/service/gpu-cloud) (observed on 2/18/2025).
 ### Multi-stream asynchronous performance (measured with vLLM version 0.7.2)
       <th>Model</th>
       <th>Average Cost Reduction</th>
       <th>Maximum throughput (QPS)</th>
+      <th>Queries Per Dollar</th>
       <th>Maximum throughput (QPS)</th>
+      <th>Queries Per Dollar</th>
       <th>Maximum throughput (QPS)</th>
+      <th>Queries Per Dollar</th>
     </tr>
   </thead>
   <tbody style="text-align: center">
       <td>6777</td>
     </tr>
   </tbody>
+</table>
+**Use case profiles: Image Size (WxH) / prompt tokens / generation tokens
+**QPS: Queries per second.
+**QPD: Queries per dollar, based on on-demand cost at [Lambda Labs](https://lambdalabs.com/service/gpu-cloud) (observed on 2/18/2025).