---
library_name: transformers
tags:
- prime-rl
- verifiers
- prime-intellect
- reinforcement-learning
- reasoning
- agentic
- mixture-of-experts
license: mit
language:
- en
base_model: PrimeIntellect/INTELLECT-3
pipeline_tag: text-generation
---
# INTELLECT-3 AWQ - INT4
## Model Details
### Quantization Details
- **Quantization Method:** cyankiwi AWQ v1.0
- **Bits:** 8
- **Group Size:** 32
- **Calibration Dataset:** [nvidia/Llama-Nemotron-Post-Training-Dataset](https://huggingface.co/datasets/nvidia/Llama-Nemotron-Post-Training-Dataset)
- **Quantization Tool:** [llm-compressor](https://github.com/vllm-project/llm-compressor)
### Memory Usage
| **Type** | **INTELLECT-3** | **INTELLECT-3-AWQ-8bit** |
|:---------------:|:----------------:|:----------------:|
| **Memory Size** | 199.0 GB | 107.7 GB |
| **KV Cache per Token** | 61.3 kB | 30.7 kB |
| **KV Cache per Context** | 7.7 GB | 3.8 GB |
## Inference
### Prerequisite
```bash
pip install -U vllm
```
### Basic Usage
```bash
vllm serve cyankiwi/INTELLECT-3-AWQ-8bit \
--tensor-parallel-size 2 \
--enable-auto-tool-choice \
--tool-call-parser qwen3_coder \
--reasoning-parser deepseek_r1
```
## Additional Information
### Known Issues
- `tensor-parallel-size > 2` requires `--enable-expert-parallel`
- No MTP implementation
### Changelog
- **v0.9.0** - Initial quantized release without MTP implementation
### Authors
- **Name:** Ton Cao
- **Contacts:** ton@cyan.kiwi
# INTELLECT-3
INTELLECT-3: A 100B+ MoE trained with large-scale RL
Trained with prime-rl and verifiers
Environments released on Environments Hub
Read the Blog & Technical Report
X | Discord | Prime Intellect Platform
## Introduction
**INTELLECT-3** is a 106B (A12B) parameter Mixture-of-Experts reasoning model post-trained from [GLM-4.5-Air-Base](https://huggingface.co/zai-org/GLM-4.5-Air-Base) using supervised fine-tuning (SFT) followed by large-scale reinforcement learning (RL).
Training was performed with [prime-rl](https://github.com/PrimeIntellect-ai/prime-rl) using environments built with the [verifiers](https://github.com/PrimeIntellect-ai/verifiers) library.
All training and evaluation environments are available on the [Environments Hub](https://app.primeintellect.ai/dashboard/environments).
The model, training frameworks, and environments are open-sourced under fully-permissive licenses (MIT and Apache 2.0).
For more details, see the [technical report](https://storage.googleapis.com/intellect-3-paper/INTELLECT_3_Technical_Report.pdf).
## Evaluation
INTELLECT-3 achieves best-in-class performance on math, coding, and reasoning benchmarks:
| Benchmark | MATH-500 | AIME24 | AIME25 | LCB | GPQA | HLE | MMLU-Pro |
|-----------|----------|---------|---------|--------|------|-----|----------|
| INTELLECT-3 | **98.1** | **90.8** | **88.0** | 69.3 | 74.4 | 14.6 | 81.9 |
| GLM-4.5-Air | 97.8 | 84.6 | 82.0 | 61.5 | 73.3 | 13.3 | 73.9 |
| GLM-4.5 | 97.0 | 85.8 | 83.3 | 64.5 | 77.0 | 14.8 | 83.5 |
| DeepSeek R1 0528 | 87.3 | 83.2 | 73.4 | 62.5 | 77.5 | 15.9 | 75.3 |
| DeepSeek v3.2 | 96.8 | 88.1 | 84.7 | **71.6** | **81.4** | **17.9** | **84.6** |
| GPT-O5S 120B | 96.0 | 75.8 | 77.7 | 69.9 | 70.0 | 10.6 | 67.1 |
## Model Variants
| Model | HuggingFace |
|-------|-------------|
| INTELLECT-3 | [PrimeIntellect/INTELLECT-3](https://huggingface.co/PrimeIntellect/INTELLECT-3) |
| INTELLECT-3-FP8 | [PrimeIntellect/INTELLECT-3-FP8](https://huggingface.co/PrimeIntellect/INTELLECT-3-FP8) |
## Serving with vLLM
The BF16 version can be served on 2x H200s:
```bash
vllm serve PrimeIntellect/INTELLECT-3 \
--tensor-parallel-size 2 \
--enable-auto-tool-choice \
--tool-call-parser qwen3_coder \
--reasoning-parser deepseek_r1
```
The FP8 version can be served on a single H200:
```bash
vllm serve PrimeIntellect/INTELLECT-3-FP8 \
--enable-auto-tool-choice \
--tool-call-parser qwen3_coder \
--reasoning-parser deepseek_r1
```
## Citation
```bibtex
@misc{intellect3,
title={INTELLECT-3: Technical Report},
author={Prime Intellect Team},
year={2025},
url={https://huggingface.co/PrimeIntellect/INTELLECT-3}
}
```
