Hacker News new | ask | show | jobs
Deploy dedicated DeepSeek 32B on L40 GPUs ($8/hour) (lightning.ai)
19 points by wfalcon 500 days ago
6 comments
woodr77 498 days ago
Everyone's saying I needed H100s for this. L40 is way easier for me to get my hands on. great news.
link
ashenWon 500 days ago
Is this running ollama, vllm or sglang under the hood? Curious about these performance numbers.
link
lmilad 500 days ago
How well does DeepSeek R1 handle generating long pieces of text with Qwen 32B?
link
tchaton84 500 days ago
Does it support largest Deepseek model ?
link
yewnork 500 days ago
curious the performance / price tradeoffs between deepseek-r1 671b, 70b, 32b
link
neilbhatt 500 days ago
nice, i can actually use my AWS start up creds
link