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

[woodr77]

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

[ashenWon]

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

[lmilad]

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

[tchaton84]

Does it support largest Deepseek model ?

[yewnork]

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

[neilbhatt]

nice, i can actually use my AWS start up creds