---
title: "L40S rental in Uzbekistan: early access | UZ Dynamics"
description: "NVIDIA L40S: early access by request; availability, form factor pending. 48 GB GDDR6 · 0.86 TB/s · PCIe 4. LLMs up to 32B in FP8 on one GPU (estimate)."
url: "https://uzdynamics.ai/en/gpus/l40s"
lang: "en"
image: "https://uzdynamics.ai/en/gpus/l40s/opengraph-image/card?f08c4f789845417d"
alternates:
  ru: "https://uzdynamics.ai/ru/gpus/l40s"
  uz: "https://uzdynamics.ai/uz/gpus/l40s"
  en: "https://uzdynamics.ai/en/gpus/l40s"
---

> For an index of this site's pages, see [llms.txt](https://uzdynamics.ai/llms.txt). A markdown copy of each page is at its address with `.md` appended.

# NVIDIA L40S rental: early access

Ada Lovelace · PCIe (being confirmed)

We’re collecting early-access requests. We’re placing our capacity in Uzbekistan. We don’t publish prices yet. We’ll confirm availability in our reply.

L40S

[Request L40S](https://uzdynamics.ai/en/request?source=gpu-page%3Al40s&gpu=l40s)

We’ll reply with terms for your workload. Nothing to pay before the contract.

- **Memory per GPU:** 48 GB GDDR6
- **Memory bandwidth:** 0.86 TB/s
- **GPU interconnect:** PCIe 4, no NVLink

## NVIDIA L40S specifications

- **Architecture:** Ada Lovelace
- **Announced:** 2023
- **Memory:** 48 GB
- **Memory type:** GDDR6
- **Memory bandwidth:** 0.86 TB/s
- **FP32:** 91.6 TFLOPS
- **FP16/BF16, dense:** 362.05 TFLOPS
- **FP8, dense:** 733 TFLOPS
- **FP4, dense:** none
- **FP64:** not in NVIDIA’s card specs
- **RT cores:** yes
- **NVENC/NVDEC:** NVENC 3, NVDEC 3
- **MIG:** none
- **GPU interconnect:** PCIe 4, no NVLink
- **Power (TDP/TGP):** 350 W
- **Form factor:** PCIe (being confirmed)

Memory is specified per GPU. Multiple GPUs have separate memory: using a larger model across them requires compatible software and model partitioning. NVLink does not make them one GPU.

The L40S form factor is still being confirmed. Specs from NVIDIA’s official materials, checked 26 September 2026.

## The L40S by workload

- Inference: LLMs up to 32B in FP8 on one GPU
- Fine-tuning: QLoRA up to 32B, LoRA up to 14B on one GPU
- Training from scratch: models up to 1B on one GPU
- Rendering: scenes up to 32 GB
- FP64 computing: not suited to this GPU

An estimate from open formulas, not a benchmark or an invoice.

## Servers with the NVIDIA L40S

Server configuration (CPU, RAM, disk, network) is being confirmed.

Sizing assumption: up to 8 GPUs per server. We’ll confirm the actual configuration in our reply.

[More than 8 GPUs? Discuss a cluster](https://uzdynamics.ai/en/enterprise?source=gpu-page-cluster%3Al40s&gpu=l40s&count=more)

## Sources

- [NVIDIA L40S](https://www.nvidia.com/en-us/data-center/l40s/)
- [NVIDIA Video Encode and Decode Support Matrix](https://developer.nvidia.com/video-encode-decode-support-matrix)
- [NVIDIA Multi-Instance GPU User Guide](https://docs.nvidia.com/datacenter/tesla/mig-user-guide/latest/supported-gpus.html)
- [NVIDIA Newsroom, August 8, 2023](https://nvidianews.nvidia.com/news/nvidia-global-data-center-system-manufacturers-to-supercharge-generative-ai-and-industrial-digitalization)

## Similar GPUs

- [NVIDIA RTX 6000 Ada Generation](https://uzdynamics.ai/en/gpus/rtx-6000-ada)
  48 GB GDDR6 · 0.96 TB/s · PCIe 4
  RTX 6000 Ada leads on 1 of 5 metrics. RTX 6000 Ada has more memory bandwidth (0.96 vs 0.86 TB/s). Equal: memory size. Nearly equal (under 1% apart): FP32, FP16/BF16, FP8.
- [NVIDIA L4](https://uzdynamics.ai/en/gpus/l4)
  24 GB GDDR6 · 0.3 TB/s · PCIe 4
  L40S leads on all 5 metrics. L40S has more FP8 (733 vs 242 TFLOPS) and FP32 (91.6 vs 30.3 TFLOPS).

## All GPUs in the catalogue

- [B300](https://uzdynamics.ai/en/gpus/b300)
- [B200](https://uzdynamics.ai/en/gpus/b200)
- [H200](https://uzdynamics.ai/en/gpus/h200)
- [H100](https://uzdynamics.ai/en/gpus/h100)
- [A100](https://uzdynamics.ai/en/gpus/a100)
- [RTX PRO 6000](https://uzdynamics.ai/en/gpus/rtx-pro-6000)
- [L4](https://uzdynamics.ai/en/gpus/l4)
- [RTX 6000 Ada](https://uzdynamics.ai/en/gpus/rtx-6000-ada)
- [RTX A6000](https://uzdynamics.ai/en/gpus/rtx-a6000)
- [RTX A5000](https://uzdynamics.ai/en/gpus/rtx-a5000)

[Request L40S](https://uzdynamics.ai/en/request?source=gpu-page-end%3Al40s&gpu=l40s)

We’ll reply with terms for your workload. Nothing to pay before the contract.

```json
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"UZ Dynamics","item":"https://uzdynamics.ai/en"},{"@type":"ListItem","position":2,"name":"GPU catalogue","item":"https://uzdynamics.ai/en/gpus"},{"@type":"ListItem","position":3,"name":"L40S","item":"https://uzdynamics.ai/en/gpus/l40s"}]}
```