NVIDIA L40S GPUs are here
📰 Replicate Blog
NVIDIA L40S GPUs are now available on Replicate, offering 40% faster performance than A40 GPUs, with migration of existing models and deployments starting soon
Action Steps
- Check the Replicate documentation to learn how to switch existing models and deployments to L40S GPUs
- Review the pricing changes and plan for potential cost adjustments
- Test and optimize models on L40S GPUs to take advantage of the improved performance
Who Needs to Know This
Developers and data scientists on a team can benefit from the improved performance and potential cost savings of L40S GPUs, while product managers and entrepreneurs should be aware of the pricing changes and plan accordingly
Key Insight
💡 L40S GPUs offer improved performance and potential cost savings, but may require adjustments to pricing and model optimization
Share This
🚀 NVIDIA L40S GPUs are here! 40% faster than A40 GPUs, with migration starting soon. Check out the details and plan for the change #GPUs #AI #ML
Key Takeaways
NVIDIA L40S GPUs are now available on Replicate, offering 40% faster performance than A40 GPUs, with migration of existing models and deployments starting soon
Full Article
# NVIDIA L40S GPUs are here – Replicate blog
[Replicate has joined Cloudflare](https://replicate.com/blog/replicate-cloudflare)
[](https://replicate.com/)
cmd+k
[Explore](https://replicate.com/explore)[Pricing](https://replicate.com/pricing)[Enterprise](https://replicate.com/enterprise)[Docs](https://replicate.com/docs)[Blog](https://replicate.com/blog)[Sign in](https://replicate.com/signin)[Try for free](https://replicate.com/signin)
Menu
[Explore](https://replicate.com/explore)[Pricing](https://replicate.com/pricing)[Enterprise](https://replicate.com/enterprise)[Docs](https://replicate.com/docs)[Blog](https://replicate.com/blog)[Sign in](https://replicate.com/signin)[Try for free](https://replicate.com/signin)
* * *
[Compare models in the Playground](https://replicate.com/playground)
* Replicate
* [Blog](https://replicate.com/blog)
# NVIDIA L40S GPUs are here
Posted November 15, 2024 by
* [zeke](https://replicate.com/zeke)
Today we added NVIDIA L40S GPUs to our [supported hardware types](https://replicate.com/pricing). These new GPUs are around 40% faster than A40 GPUs.
We’re also going to be removing support for A40 GPUs. We will begin migrating all existing models and deployments from A40 GPUs to L40S GPUs over the coming weeks. You’ll continue to pay the same price for your private models and deployments, but you might pay more if you’re using public models or training models on A40 GPUs.
You can now run L40S GPUs for any [new models](https://replicate.com/docs/topics/models/create-a-model), [existing models](https://replicate.com/docs/topics/models/hardware), or [deployments](https://replicate.com/docs/topics/deployments). To learn how to change the hardware type for your models and deployments, [check out the docs](https://replicate.com/docs/topics/models/hardware).
Starting today, you have the option to [switch any of your existing models and deployments to L40S GPUs](https://replicate.com/docs/topics/models/hardware), but you are not required to do so. If you choose not to switch, your models and deployments will continue to run on A40 GPUs for another few weeks until we migrate them to L40S GPUs.
## [](https://replicate.com/blog/nvidia-l40s-gpus-are-here#migration-timeline)Migration timeline
To give you better performance per dollar, we will begin migrating all existing models and deployments from A40 GPUs to L40S GPUs over the coming weeks:
* **2024-12-02: Public model migration.** We will begin migrating all _public_ models running on A40 GPUs, and will finish migrating all models by 2024-12-04.
* **2024-12-09: Private model and deployment migration.** We will begin migrating all _private_ models and deployments running on A40 GPUs, and will finish migrating all models by 2024-12-11. A40 GPUs will no longer be available after this date.
## [](https://replicate.com/blog/nvidia-l40s-gpus-are-here#speed-and-cost)Speed and cost
The L40S GPUs are [more expensive per second](https://replicate.com/pricing) than the A40 GPUs, but they are also faster.
Our benchmarks across the highest-usage A40 models today show a [~40% median speed improvement](https://observablehq.com/d/72549bf2858302e5) when migrating from A40 GPUs to L40S GPUs. For more detail, see our [Observable notebook](https://observablehq.com/d/72549bf2858302e5) which covers our benchmarking methodology, collection methods, and results.
How much you’ll pay if your models are migrated for L40S GPUs depends on what you’re using them for:
* **Private models and deployments:** If you’re currently using A40 GPUs for private models or deployments, this is all good news: you’ll continue to pay the same price you pay today after we’ve migrated them to L40S GPUs. Because these new GPUs are faster, your bill will probably go down, and at worst stay the same.
* **Public models and training:** If you’re using public models or training models on A40 GPUs, you’ll pay the new price of $3.51 per hour for L40S GPUs.
* If you’re using
[Replicate has joined Cloudflare](https://replicate.com/blog/replicate-cloudflare)
[](https://replicate.com/)
cmd+k
[Explore](https://replicate.com/explore)[Pricing](https://replicate.com/pricing)[Enterprise](https://replicate.com/enterprise)[Docs](https://replicate.com/docs)[Blog](https://replicate.com/blog)[Sign in](https://replicate.com/signin)[Try for free](https://replicate.com/signin)
Menu
[Explore](https://replicate.com/explore)[Pricing](https://replicate.com/pricing)[Enterprise](https://replicate.com/enterprise)[Docs](https://replicate.com/docs)[Blog](https://replicate.com/blog)[Sign in](https://replicate.com/signin)[Try for free](https://replicate.com/signin)
* * *
[Compare models in the Playground](https://replicate.com/playground)
* Replicate
* [Blog](https://replicate.com/blog)
# NVIDIA L40S GPUs are here
Posted November 15, 2024 by
* [zeke](https://replicate.com/zeke)
Today we added NVIDIA L40S GPUs to our [supported hardware types](https://replicate.com/pricing). These new GPUs are around 40% faster than A40 GPUs.
We’re also going to be removing support for A40 GPUs. We will begin migrating all existing models and deployments from A40 GPUs to L40S GPUs over the coming weeks. You’ll continue to pay the same price for your private models and deployments, but you might pay more if you’re using public models or training models on A40 GPUs.
You can now run L40S GPUs for any [new models](https://replicate.com/docs/topics/models/create-a-model), [existing models](https://replicate.com/docs/topics/models/hardware), or [deployments](https://replicate.com/docs/topics/deployments). To learn how to change the hardware type for your models and deployments, [check out the docs](https://replicate.com/docs/topics/models/hardware).
Starting today, you have the option to [switch any of your existing models and deployments to L40S GPUs](https://replicate.com/docs/topics/models/hardware), but you are not required to do so. If you choose not to switch, your models and deployments will continue to run on A40 GPUs for another few weeks until we migrate them to L40S GPUs.
## [](https://replicate.com/blog/nvidia-l40s-gpus-are-here#migration-timeline)Migration timeline
To give you better performance per dollar, we will begin migrating all existing models and deployments from A40 GPUs to L40S GPUs over the coming weeks:
* **2024-12-02: Public model migration.** We will begin migrating all _public_ models running on A40 GPUs, and will finish migrating all models by 2024-12-04.
* **2024-12-09: Private model and deployment migration.** We will begin migrating all _private_ models and deployments running on A40 GPUs, and will finish migrating all models by 2024-12-11. A40 GPUs will no longer be available after this date.
## [](https://replicate.com/blog/nvidia-l40s-gpus-are-here#speed-and-cost)Speed and cost
The L40S GPUs are [more expensive per second](https://replicate.com/pricing) than the A40 GPUs, but they are also faster.
Our benchmarks across the highest-usage A40 models today show a [~40% median speed improvement](https://observablehq.com/d/72549bf2858302e5) when migrating from A40 GPUs to L40S GPUs. For more detail, see our [Observable notebook](https://observablehq.com/d/72549bf2858302e5) which covers our benchmarking methodology, collection methods, and results.
How much you’ll pay if your models are migrated for L40S GPUs depends on what you’re using them for:
* **Private models and deployments:** If you’re currently using A40 GPUs for private models or deployments, this is all good news: you’ll continue to pay the same price you pay today after we’ve migrated them to L40S GPUs. Because these new GPUs are faster, your bill will probably go down, and at worst stay the same.
* **Public models and training:** If you’re using public models or training models on A40 GPUs, you’ll pay the new price of $3.51 per hour for L40S GPUs.
* If you’re using
DeepCamp AI