Instructions to use PrimeIntellect/glm4-moe-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PrimeIntellect/glm4-moe-tiny with Transformers:

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

pipe = pipeline("text-generation", model="PrimeIntellect/glm4-moe-tiny")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PrimeIntellect/glm4-moe-tiny")
model = AutoModelForCausalLM.from_pretrained("PrimeIntellect/glm4-moe-tiny")
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/glm4-moe-tiny with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PrimeIntellect/glm4-moe-tiny"
# 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/glm4-moe-tiny",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PrimeIntellect/glm4-moe-tiny

SGLang

How to use PrimeIntellect/glm4-moe-tiny 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/glm4-moe-tiny" \
    --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/glm4-moe-tiny",
		"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/glm4-moe-tiny" \
        --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/glm4-moe-tiny",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PrimeIntellect/glm4-moe-tiny with Docker Model Runner:
```
docker model run hf.co/PrimeIntellect/glm4-moe-tiny
```

glm4-moe-tiny

A small (~543M parameter) GLM-4 MoE model for testing only. It is generally compatible with vLLM and HuggingFace Transformers but is meant to be used with prime-rl.

Fine-tuned on PrimeIntellect/Reverse-Text-SFT to provide a non-trivial distribution for KL divergence during RL.

Quick Start

uv run rl @ configs/ci/integration/rl_moe/glm4_moe.toml

See the Testing MoE at Small Scale guide for full instructions.

Model Details

Parameter	Value
Hidden size	1024
Layers	24
Experts	8
Active experts	4
Parameters	~543M

PrimeIntellect
/

glm4-moe-tiny

glm4-moe-tiny

Quick Start

Model Details

Links