> ## Documentation Index
> Fetch the complete documentation index at: https://docs.coreweave.com/llms.txt
> Use this file to discover all available pages before exploring further.

# L40S

> Specifications and availability for the L40S GPU instance

These instances feature eight NVIDIA L40S GPUs, each with 48 GB of GDDR6 memory. The L40S is a compute-optimized version of the L40, specifically tuned to deliver higher performance for AI and data science workloads. Connected via PCIe, these GPUs are a cost-effective choice for scaling out inference and for fine-tuning mainstream models. They provide a strong balance of performance and value for enterprise AI deployment.

## Specifications

| Feature                   | Detail                                                   |
| :------------------------ | :------------------------------------------------------- |
| **Category**              | Professional AI & Graphics                               |
| **Instance ID**           | `gd-8xl40s-i128`                                         |
| **GPU**                   | 8x NVIDIA L40S                                           |
| **GPU RAM**               | 48 GB                                                    |
| **GPU Connectivity**      | PCIe                                                     |
| **CPU Model**             | Intel Sapphire Rapids 8462Y+ (2.80 GHz)                  |
| **vCPUs**                 | 128                                                      |
| **RAM**                   | 1024 GB                                                  |
| **Local Storage**         | 7.68 TB                                                  |
| **Network Speed**         | Dual-port 100GbE                                         |
| **Default GPU driver**    | `595`                                                    |
| **Compatible GPU driver** | `535`, `580`, `595`                                      |
| **Availability**          | [**US-EAST-04A**](/platform/regions/us-east#us-east-04a) |

## Primary use cases

High-throughput inference, efficient fine-tuning, video analytics, and other compute-focused AI tasks.

## Recommended models

Inference for models up to \~40B parameters like Gemma 4 26B or Qwen 3.6 27B; efficient fine-tuning of smaller sub-15B models.