Inference models

Recent
Lambda Inference API
deepseek-r1

Introduction The DeepSeek R1 model is a text generation model based on the transformer architecture, specifically the deepseek_v3 model type. It was developed ...

Lambda Inference API
qwen25-coder-32b-instruct

Introduction The Qwen2.5-Coder-32B-Instruct model is a type of qwen2 model, which is a transformer-based architecture. It was developed by Qwen for ...

deepseek-v3-0324

Introduction The DeepSeek V3 0324 model is a type of deepseek_v3 model, built using the transformers library. It employs a specific architecture and was ...

1 2 3

Ready to build?

Contact us to learn more about our Managed Kubernetes service and how it can help you accelerate your AI initiatives.