Instructions to use FirstPrinciplesLabs/quark with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FirstPrinciplesLabs/quark with Transformers:

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

pipe = pipeline("image-text-to-text", model="FirstPrinciplesLabs/quark")
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("FirstPrinciplesLabs/quark")
model = AutoModelForMultimodalLM.from_pretrained("FirstPrinciplesLabs/quark", 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 FirstPrinciplesLabs/quark with vLLM:

Install from pip and serve model

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

SGLang

How to use FirstPrinciplesLabs/quark 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 "FirstPrinciplesLabs/quark" \
    --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": "FirstPrinciplesLabs/quark",
		"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 "FirstPrinciplesLabs/quark" \
        --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": "FirstPrinciplesLabs/quark",
		"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 FirstPrinciplesLabs/quark with Docker Model Runner:
```
docker model run hf.co/FirstPrinciplesLabs/quark
```

chengfp-eng commited on 8 days ago

Commit

2720954

verified ·

1 Parent(s): 19c9738

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -8

README.md CHANGED Viewed

@@ -15,16 +15,16 @@ tags:
 - qwen3.5
 ---
-# Theo-Quark
-Theo-Quark is a 9B reasoning model for physics, science and maths, built by [FirstPrinciples](https://firstprinciples.com/). The base model is
 [Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) with additional post-training: supervised fine-tuning on
 our curated physics, maths and coding mix.
 It outperforms the base model on a range of benchmarks, and reaches
 graduate-level science scores comparable to much larger open models.
-Theo-Quark is the first in a series of small, powerful scientific reasoning models. You can use Theo-Quark locally or natively on [Theo Platform](https://firstprinciples.com/sign-up).
 ## Results
@@ -33,7 +33,7 @@ up to 131,072 output tokens, and following the Qwen3.5 model card's sampling set
 AIME 2025 is averaged over 16 samples per problem and GPQA Diamond over 8. HLE (text-only, 2,158 questions)
 is graded by Qwen3.5-27B as judge.
-| Benchmark | Qwen3.5-9B | **Theo-Quark** | Cut off at 131K: Qwen3.5-9B | Cut off at 131K: Theo-Quark |
 |---|---|---|---|---|
 | GPQA Diamond | 81.6 | **87.4** | 0% | 0.3% |
 | AIME 2025 | 86.9 | **91.7** | 0% | 3.3% |
@@ -48,7 +48,7 @@ Both models were measured by us with the same setup. "Cut off" is the share of a
 | Model | Size | GPQA Diamond | AIME 2025 | HLE |
 |---|---|---|---|---|
-| **Theo-Quark** | 9B | **87.4** | **91.7** | **22.7** |
 | Qwen3-8B | 8B | 59.6 | 69.3 | 4.4 |
 | NVIDIA Nemotron Nano 9B v2 | 9B | 64.0 | 72.1 | 6.5 |
 | gpt-oss-20b | 21B | 71.5 | 91.7 | 10.9 |
@@ -62,7 +62,7 @@ Both models were measured by us with the same setup. "Cut off" is the share of a
 ## Training data
-Theo-Quark was fine-tuned on our curated mix of about 200,000 physics, science, maths and coding problems,
 each with a worked solution written by [Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next).
 Solutions were checked for correctness, and problems overlapping the benchmarks above were removed. Most
 examples include the full reasoning; a fifth are direct answers, so the model keeps both thinking and
@@ -70,10 +70,10 @@ non-thinking modes.
 ## Usage
-Theo-Quark runs anywhere Qwen3.5-9B does (Transformers, vLLM, SGLang). We recommend an output budget of 131,072 tokens for best performance.
 ```bash
-vllm serve FirstPrinciplesLabs/theo-quark \
   --max-model-len 135168 --reasoning-parser qwen3
 ```

 - qwen3.5
 ---
+# Quark
+Quark is a 9B reasoning model for physics, science and maths, built by [FirstPrinciples](https://firstprinciples.com/). The base model is
 [Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) with additional post-training: supervised fine-tuning on
 our curated physics, maths and coding mix.
 It outperforms the base model on a range of benchmarks, and reaches
 graduate-level science scores comparable to much larger open models.
+Quark is the first in a series of small, powerful scientific reasoning models. You can use Quark locally or natively on [Theo Platform](https://firstprinciples.com/sign-up).
 ## Results
 AIME 2025 is averaged over 16 samples per problem and GPQA Diamond over 8. HLE (text-only, 2,158 questions)
 is graded by Qwen3.5-27B as judge.
+| Benchmark | Qwen3.5-9B | **Quark** | Cut off at 131K: Qwen3.5-9B | Cut off at 131K: Quark |
 |---|---|---|---|---|
 | GPQA Diamond | 81.6 | **87.4** | 0% | 0.3% |
 | AIME 2025 | 86.9 | **91.7** | 0% | 3.3% |
 | Model | Size | GPQA Diamond | AIME 2025 | HLE |
 |---|---|---|---|---|
+| **Quark** | 9B | **87.4** | **91.7** | **22.7** |
 | Qwen3-8B | 8B | 59.6 | 69.3 | 4.4 |
 | NVIDIA Nemotron Nano 9B v2 | 9B | 64.0 | 72.1 | 6.5 |
 | gpt-oss-20b | 21B | 71.5 | 91.7 | 10.9 |
 ## Training data
+Quark was fine-tuned on our curated mix of about 200,000 physics, science, maths and coding problems,
 each with a worked solution written by [Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next).
 Solutions were checked for correctness, and problems overlapping the benchmarks above were removed. Most
 examples include the full reasoning; a fifth are direct answers, so the model keeps both thinking and
 ## Usage
+Quark runs anywhere Qwen3.5-9B does (Transformers, vLLM, SGLang). We recommend an output budget of 131,072 tokens for best performance.
 ```bash
+vllm serve FirstPrinciplesLabs/quark \
   --max-model-len 135168 --reasoning-parser qwen3
 ```