Deploy dedicated DeepSeek 32B on L40 GPUs ($8/hour)
1–7 of 7 posts
Re: Deploy dedicated DeepSeek 32B on L40 GPUs ($8/hour)
#2nice, i can actually use my AWS start up creds
Re: Deploy dedicated DeepSeek 32B on L40 GPUs ($8/hour)
#3Does it support largest Deepseek model ?
Re: Deploy dedicated DeepSeek 32B on L40 GPUs ($8/hour)
#4curious the performance / price tradeoffs between deepseek-r1 671b, 70b, 32b
Re: Deploy dedicated DeepSeek 32B on L40 GPUs ($8/hour)
#5How well does DeepSeek R1 handle generating long pieces of text with Qwen 32B?
Re: Deploy dedicated DeepSeek 32B on L40 GPUs ($8/hour)
#6Is this running ollama, vllm or sglang under the hood? Curious about these performance numbers.
Re: Deploy dedicated DeepSeek 32B on L40 GPUs ($8/hour)
#7Everyone's saying I needed H100s for this. L40 is way easier for me to get my hands on. great news.