Content
@
0 reply
0 recast
0 reaction
ππͺπΎπ‘π‘πΎ
@gm8xx8
Serverless Inference with Hugging Face and NVIDIA NIMs enterprise hub deets: - uses NVIDIA DGX Cloud and NIMs. - models: includes 7 open LLMs, includes llama 3.1 70B and mixtral 8x22B. - pricing: $0.0023 per second per GPU, pay-as-you-go. - supports OpenAI API standards. https://huggingface.co/blog/inference-dgx-cloud
0 reply
0 recast
5 reactions
