---
title: "ESM2 Quantized Models"
---

## ESM2 Quantized

ESM2 Quantized is an adapted version of the ESM2 architectures. It uses local attention instead of global attention, allowing for models with longer input sizes. ESM2 Quantized models have a context size of 2,050, double that of the standard ESM2 model. This kind of model was trained with int4 quantization. Several ESM2 Quantized models are available:

| Model | Num layers |
|------------------------------|----|
| [gabrielbianchin/esm2_t36_long_int4](https://huggingface.co/gabrielbianchin/esm2_t36_long_int4) | 36 |
| [gabrielbianchin/esm2_t33_long_int4](https://huggingface.co/gabrielbianchin/esm2_t33_long_int4) | 33 | 
| [gabrielbianchin/esm2_t30_long_int4](https://huggingface.co/gabrielbianchin/esm2_t30_long_int4) | 30 | 
| [gabrielbianchin/esm2_t12_long_int4](https://huggingface.co/gabrielbianchin/esm2_t12_long_int4) | 12 | 
| [gabrielbianchin/esm2_t6_long_int4](https://huggingface.co/gabrielbianchin/esm2_t6_long_int4)  | 6 | 



For detailed information, please refer to the paper.