Instructions to use PrimeIntellect/INTELLECT-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PrimeIntellect/INTELLECT-3 with Transformers:

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

pipe = pipeline("text-generation", model="PrimeIntellect/INTELLECT-3", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PrimeIntellect/INTELLECT-3", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("PrimeIntellect/INTELLECT-3", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use PrimeIntellect/INTELLECT-3 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/PrimeIntellect/INTELLECT-3

SGLang

How to use PrimeIntellect/INTELLECT-3 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 "PrimeIntellect/INTELLECT-3" \
    --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": "PrimeIntellect/INTELLECT-3",
		"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 "PrimeIntellect/INTELLECT-3" \
        --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": "PrimeIntellect/INTELLECT-3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PrimeIntellect/INTELLECT-3 with Docker Model Runner:
```
docker model run hf.co/PrimeIntellect/INTELLECT-3
```

SeasonalFall84 commited on Dec 2, 2025

Commit

75d6bc4

verified ·

1 Parent(s): ff39d4a

Add model-index metadata for benchmark results

Browse files

This PR adds machine-readable evaluation metadata to the model card using the `model-index` format.

## What This Adds

Structured YAML metadata for 7 benchmark(s) from the README:

- MATH-500: 98.1
- AIME24: 90.8
- AIME25: 88.0
- LCB: 69.3
- GPQA: 74.4
- HLE: 14.6
- MMLU-Pro: 81.9

## Why This Helps

Adding structured benchmark metadata enables:

1. **Automatic Leaderboard Inclusion** - Model appears on Hugging Face leaderboards and Papers with Code
2. **Better Discoverability** - Users can search/filter models by benchmark scores
3. **Machine-Readable Data** - Tools and APIs can query model performance programmatically

## What Doesn't Change

- ✅ Existing README content stays the same
- ✅ Markdown benchmark tables remain unchanged
- ✅ Only adds metadata to the YAML frontmatter

Thank you for open-sourcing INTELLECT-3! This contribution helps the community compare and discover your work.

Files changed (1) hide show

README.md +33 -0

README.md CHANGED Viewed

@@ -14,6 +14,39 @@ language:
 base_model:
 - zai-org/GLM-4.5-Air-Base
 pipeline_tag: text-generation
 ---
 # INTELLECT-3

 base_model:
 - zai-org/GLM-4.5-Air-Base
 pipeline_tag: text-generation
+model-index:
+- name: INTELLECT-3
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: Benchmarks
+      type: benchmark
+    metrics:
+    - name: MATH-500
+      type: math_500
+      value: 98.1
+    - name: AIME24
+      type: aime24
+      value: 90.8
+    - name: AIME25
+      type: aime25
+      value: 88.0
+    - name: LCB
+      type: lcb
+      value: 69.3
+    - name: GPQA
+      type: gpqa
+      value: 74.4
+    - name: HLE
+      type: hle
+      value: 14.6
+    - name: MMLU-Pro
+      type: mmlu_pro
+      value: 81.9
+    source:
+      name: Model README
+      url: https://huggingface.co/PrimeIntellect/INTELLECT-3
 ---
 # INTELLECT-3