HNGlance

Top Best New Show

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

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

by wfalcon • 1 year ago

19 6 1 year ago

LI

Related Stories

Loading related stories...

Comments

6

neilbhatt• 1 year ago

nice, i can actually use my AWS start up creds

tchaton84• 1 year ago

Does it support largest Deepseek model ?

yewnork• 1 year ago

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

lmilad• 1 year ago

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

ashenWon• 1 year ago

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

woodr77• 1 year ago

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

Source preview

lightning.ai

HNGlance

© 2024-2026 HN Glance. Story content belongs to its original sources.

Privacy
Terms