TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

We're Cutting L40S Prices in Half

59 pointsby LukeLambert9 months ago

8 comments

zackangelo9 months ago
L40S has 48GB of RAM, curious how they&#x27;re able to run Llama 3.1 70B on it. The weights alone would exceed this. Maybe they mean quantized&#x2F;fp8?<p>I just had to implement GPU clustering in my inference stack to support Llama 3.1 70b, and even then I needed 2xA100 80GB SXMs.<p>I was initially running my inference servers on fly.io because they were so easy to get started with. But I eventually moved elsewhere because the prices were so high. I pointed out to someone there that e-mailed me that it was really expensive vs. others and they basically just waved me away.<p>For reference, you can get an A100 SXM 80GB spot instance on google cloud right now for $2.04&#x2F;hr ($5.07 regular).
评论 #41262626 未加载
nknealk9 months ago
&gt; You can run DOOM Eternal, building the Stadia that Google couldn’t pull off, because the L40S hasn’t forgotten that it’s a graphics GPU.<p>Savage.<p>I wonder if we’ll see a resurgence of cloud game streaming
评论 #41263114 未加载
评论 #41262538 未加载
评论 #41262477 未加载
评论 #41263086 未加载
deepsquirrelnet9 months ago
I hadn’t even heard of L40S until I started renting to get more memory for small training jobs. I didn’t benchmark it, but it seemed to be pretty fast for a pcie card.<p>Amazon’s g6 instances are L4-based with 24gb vram, half the capacity of the L40S, with sagemaker in demand prices at this rate. Vast ai is cheaper, though a little more like bidding and varying in availability.
CGamesPlay9 months ago
&gt; You can run Llama 3.1 70B — the big Llama — for LLM jobs.<p>That&#x27;s the medium Llama. Does anyone know if an L40S would run the 405B version?
评论 #41262314 未加载
tazu9 months ago
Prices lowered to $1.25&#x2F;hr... still 2X vast.ai prices.
评论 #41262442 未加载
评论 #41263217 未加载
layoric9 months ago
Not as fast as the L40S, but Runpod.io has the A40 48gb for $0.28&#x2F;hr spot price, so if its mainly VRAM you need, this is a lot cheaper option. Vast.ai has it for the same price as well.
评论 #41262616 未加载
blindriver9 months ago
Suddenly cutting prices in half shows that the business model is in dire straits.
评论 #41262808 未加载
gedw999 months ago
they buy them at 12 K, so they pay them off in 1 year approx<p>nice business to be in I guess.
评论 #41268274 未加载