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 2 days ago

Commit

07f5950

verified ·

1 Parent(s): 151510a

Add HLE vs model size plots (Pareto front, 7-10.5B)

Browse files

HLE text-only accuracy vs total parameters; Quark measured by FirstPrinciples, others by Artificial Analysis (Nov 2026).

Files changed (4) hide show

.gitattributes +1 -0
README.md +15 -0
assets/hle_7_10b.png +0 -0
assets/hle_pareto.png +3 -0

.gitattributes CHANGED Viewed

@@ -37,3 +37,4 @@ tokenizer.json filter=lfs diff=lfs merge=lfs -text
 assets/quark_banner.jpg filter=lfs diff=lfs merge=lfs -text
 assets/quark_banner.png filter=lfs diff=lfs merge=lfs -text
 assets/quark_banner_final.png filter=lfs diff=lfs merge=lfs -text

 assets/quark_banner.jpg filter=lfs diff=lfs merge=lfs -text
 assets/quark_banner.png filter=lfs diff=lfs merge=lfs -text
 assets/quark_banner_final.png filter=lfs diff=lfs merge=lfs -text
+assets/hle_pareto.png filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -67,6 +67,21 @@ All were measured by us with the same setup.
 ¹ Not reported by Qwen; measured by [Artificial Analysis](https://artificialanalysis.ai/models/qwen3-5-9b) (reasoning mode, 2,158 text-only HLE questions).
 ## Q8_0 version
 A Q8_0 version (model weights quantized to 8 bits) for llama.cpp (in GGUF format) is available at

 ¹ Not reported by Qwen; measured by [Artificial Analysis](https://artificialanalysis.ai/models/qwen3-5-9b) (reasoning mode, 2,158 text-only HLE questions).
+### HLE accuracy against model size
+![HLE accuracy against total parameters, with the Pareto front](https://huggingface.co/FirstPrinciplesLabs/quark/resolve/main/assets/hle_pareto.png)
+HLE (text-only) accuracy against total parameters, log scale. Quark is on the Pareto front: no model of its size or
+smaller scores higher. The next model up the front, Qwen3.8 27B, is nearly three times its size.
+![HLE accuracy of 7–10.5B models](https://huggingface.co/FirstPrinciplesLabs/quark/resolve/main/assets/hle_7_10b.png)
+All 37 models of 7–10.5B parameters scored by Artificial Analysis. Quark leads K2 Horizon 7B by 4.5 points.
+Quark is measured by us; every other model by [Artificial Analysis](https://artificialanalysis.ai/evaluations/humanitys-last-exam)
+on the same 2,158 questions with its own grader (data retrieved November 2026). Mixture-of-experts models are plotted at
+their total size, and models without a published parameter count aren't shown.
 ## Q8_0 version
 A Q8_0 version (model weights quantized to 8 bits) for llama.cpp (in GGUF format) is available at

assets/hle_7_10b.png ADDED Viewed

assets/hle_pareto.png ADDED Viewed

Git LFS Details

SHA256: f810c411c2bc92969710a31e22fa9fbf0b24ed74e77b6d37649fa8ff98456f4e
Pointer size: 131 Bytes
Size of remote file: 239 kB