Instructions to use PixilabAI/Blink-v0.3-26B-A4B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PixilabAI/Blink-v0.3-26B-A4B-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="PixilabAI/Blink-v0.3-26B-A4B-NVFP4")
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("PixilabAI/Blink-v0.3-26B-A4B-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("PixilabAI/Blink-v0.3-26B-A4B-NVFP4", 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 PixilabAI/Blink-v0.3-26B-A4B-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PixilabAI/Blink-v0.3-26B-A4B-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PixilabAI/Blink-v0.3-26B-A4B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PixilabAI/Blink-v0.3-26B-A4B-NVFP4

SGLang

How to use PixilabAI/Blink-v0.3-26B-A4B-NVFP4 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 "PixilabAI/Blink-v0.3-26B-A4B-NVFP4" \
    --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": "PixilabAI/Blink-v0.3-26B-A4B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "PixilabAI/Blink-v0.3-26B-A4B-NVFP4" \
        --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": "PixilabAI/Blink-v0.3-26B-A4B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PixilabAI/Blink-v0.3-26B-A4B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/PixilabAI/Blink-v0.3-26B-A4B-NVFP4
```

Add Typed Decisions benchmark eval results

by codelion - opened 4 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+24

-0

codelion

4 days ago

Adds Typed Decisions benchmark results to the model card. Evaluated on LocalLLaMA/typed-decisions, test split, 400 cases, 2,000 decisions, on 2026-10-22 via the Decision Models hosted API using model s1-fast (version s1-fast-2), which serves this model in NVFP4. Results: accuracy 0.727, KL from gold 0.153, Brier 0.079, ECE 0.129. Scored with the benchmark reference scorer, ECE uses 15 bins. One question was sent per request because that endpoint takes one question per call; most rows on the leaderboard send all five questions in one request. The author may close this PR and report their own numbers instead.

Add Typed Decisions benchmark eval resultsaaea9cd9

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment