Deploy dedicated DeepSeek 32B on L40 GPUs ($8/hour)(lightning.ai)

19 pointsby wfalconالسنة الماضية6 comments

https://lightning.ai/lightning-ai/ai-hub/temp_01jjwf2q3hpvb5aj408qk7snhc

6 comments

woodr77السنة الماضية

Everyone's saying I needed H100s for this. L40 is way easier for me to get my hands on. great news.

ashenWonالسنة الماضية

Is this running ollama, vllm or sglang under the hood? Curious about these performance numbers.

lmiladالسنة الماضية

How well does DeepSeek R1 handle generating long pieces of text with Qwen 32B?

tchaton84السنة الماضية

Does it support largest Deepseek model ?

yewnorkالسنة الماضية

curious the performance / price tradeoffs between deepseek-r1 671b, 70b, 32b

neilbhattالسنة الماضية

nice, i can actually use my AWS start up creds