Instructions to use 0xSero/INTELLECT-3-57B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 0xSero/INTELLECT-3-57B with Transformers:

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

pipe = pipeline("text-generation", model="0xSero/INTELLECT-3-57B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("0xSero/INTELLECT-3-57B")
model = AutoModelForCausalLM.from_pretrained("0xSero/INTELLECT-3-57B")
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 0xSero/INTELLECT-3-57B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0xSero/INTELLECT-3-57B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "0xSero/INTELLECT-3-57B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/0xSero/INTELLECT-3-57B

SGLang

How to use 0xSero/INTELLECT-3-57B 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 "0xSero/INTELLECT-3-57B" \
    --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": "0xSero/INTELLECT-3-57B",
		"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 "0xSero/INTELLECT-3-57B" \
        --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": "0xSero/INTELLECT-3-57B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 0xSero/INTELLECT-3-57B with Docker Model Runner:
```
docker model run hf.co/0xSero/INTELLECT-3-57B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Support this work → · X · GitHub · REAP paper · Cerebras REAP

INTELLECT-3-57B

REAP-pruned PrimeIntellect/INTELLECT-3.

At a glance


Base model	PrimeIntellect/INTELLECT-3
Format	BF16
Total params	57B
Active / token	—
Experts / layer	64
Layers	46
Hidden size	4096
Context	131,072
On-disk size	114 GB

50% expert-pruned version of PrimeIntellect/INTELLECT-3 using Cerebras REAP (Router-weighted Expert Activation Pruning).

Model Details

Property	Value
Base Model	PrimeIntellect/INTELLECT-3 (248B MoE)
Architecture	GLM-4 MoE (glm4_moe)
Compression	50% (64 experts pruned)
Remaining Experts	64 per layer
Parameters	~124B
Format	BF16 SafeTensors
Size	107 GB

REAP Configuration

dataset: 0xSero/glm47-reap-calibration-v2
samples: 1360
  - evol-codealpaca-v1: 700 (code generation)
  - xlam-function-calling-60k: 330 (function calling)
  - SWE-smith-trajectories: 330 (agentic multi-turn)
distance_measure: angular
seed: 42
model_max_length: 2048
compression_ratio: 0.50
prune_method: reap

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "0xSero/INTELLECT-3-57B",
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("0xSero/INTELLECT-3-57B", trust_remote_code=True)

messages = [{"role": "user", "content": "Write a Python function to calculate fibonacci numbers"}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)
outputs = model.generate(inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Related Models

Model	Compression	Format	Size
INTELLECT-3-REAP-50	50%	BF16	107GB
INTELLECT-3-REAP-50-W4A16	50%	W4A16 GPTQ	~30GB (coming soon)

License & citation

License inherited from the base model.

@misc{lasby2025reap,
  title  = {REAP the Experts: Why Pruning Prevails for One-Shot MoE Compression},
  author = {Mike Lasby and Ivan Lazarevich and Nish Sinnadurai and Sean Lie and Yani Ioannou and Vithursan Thangarasa},
  year   = {2025}, eprint = {2510.13999}, archivePrefix = {arXiv}
}