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

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

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

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

Does it support largest Deepseek model ?

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

nice, i can actually use my AWS start up creds