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 14 days ago

Commit

3538f83

verified ·

1 Parent(s): da9b8d3

Model card: note benchmarks were run with EvalScope

Browse files

Files changed (1) hide show

README.md +12 -4

README.md CHANGED Viewed

@@ -17,16 +17,17 @@ tags:
 # Theo-Quark
-Theo-Quark is a 9B reasoning model for physics, science and maths, built by [First Principles](https://firstprinciples.com/). It 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 model it started from on every hard benchmark we ran at 131K maximum output token limit, and reaches
 graduate-level science scores comparable to much larger open models.
 ## Results
-Accuracy (%), thinking mode, up to 131,072 output tokens, the Qwen3.5 model card's sampling settings.
 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.
@@ -40,7 +41,8 @@ is graded by Qwen3.5-27B as judge.
 Both columns were measured by us with the same setup.
-**Compared with other open models** (scores as reported by each developer):
 | Model | Size | GPQA Diamond | AIME 2025 | HLE |
 |---|---|---|---|---|
@@ -65,6 +67,12 @@ Solutions were checked for correctness, and problems overlapping the benchmarks
 examples include the full reasoning; a fifth are direct answers, so the model keeps both thinking and
 non-thinking modes.
 ## Usage
 Theo-Quark runs anywhere Qwen3.5-9B does (Transformers, vLLM, SGLang). Its answers to hard problems are

 # Theo-Quark
+Theo-Quark is a 9B reasoning model for physics, science and maths, built by First Principles. It 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.
+With room to think, it outperforms the model it started from on every hard benchmark we ran, and reaches
 graduate-level science scores comparable to much larger open models.
 ## Results
+Accuracy (%), measured with [EvalScope](https://github.com/modelscope/evalscope) and vLLM: thinking mode,
+up to 131,072 output tokens, the Qwen3.5 model card's sampling settings.
 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.
 Both columns were measured by us with the same setup.
+**Compared with other open models** (scores as reported by each developer; they use their own settings,
+mostly with shorter output limits, so small differences are not meaningful):
 | Model | Size | GPQA Diamond | AIME 2025 | HLE |
 |---|---|---|---|---|
 examples include the full reasoning; a fifth are direct answers, so the model keeps both thinking and
 non-thinking modes.
+## Training
+Full-parameter supervised fine-tuning for 6 epochs: peak learning rate 1e-5 with cosine decay, about
+1.57M tokens per step, sequences packed to 98,304 tokens, on 16 NVIDIA H200 GPUs. The architecture,
+tokenizer and chat template are unchanged from Qwen3.5-9B; the vision encoder was not trained.
 ## Usage
 Theo-Quark runs anywhere Qwen3.5-9B does (Transformers, vLLM, SGLang). Its answers to hard problems are