Skip to main content
These examples cover a variety of use cases on Baseten, from deploying your first LLM and image generation to transcription, embeddings, and RAG pipelines. Whether you’re optimizing inference with TensorRT-LLM or deploying a model with Truss, these guides help you build and scale efficiently.

​
Choosing the right engine

Not sure which engine to use? Check out our engine documentation to:
  • Select the appropriate engine for your model architecture (embeddings, dense LLMs, or MoE models)
  • Understand performance trade-offs between different engine options
  • Configure advanced features like quantization and speculative decoding
  • Optimize for your specific use case with engine-specific guidance

Deploy your first model

Fast LLMs with TensorRT-LLM

Run any LLM with vLLM

Deploy LLMs with SGLang

Transcribe audio with a Chain

Embeddings with BEI

​
Model library

For dedicated infrastructure and full control, deploy prebuilt models like DeepSeek, GLM, and Qwen from the model library. While Model APIs offer instant access to shared endpoints, the model library lets you run dedicated instances on your choice of hardware.

DeepSeek R1

Whisper V3

Qwen 2.5 32B Coder Instruct

Llama 3.3 70B Instruct

flux-schnell

MARS6

​
Training

Train and fine-tune models with Baseten’s scalable training infrastructure. From fine-tuning large language models to training custom models, our platform provides the tools and compute you need.

GPT OSS 20B with LoRA

Llama 3.1 8B SFT

Long Context Qwen3-30B

Coding with Qwen3-8B

Our training infrastructure supports popular frameworks including VERL, Megatron, and Unsloth, as well as models trained directly with Hugging Face Transformers.