‌

Model library

Browse our library of open source models that are ready to deploy behind an API endpoint in seconds.

Deploy your own model

All LLM Transcription Text to speech Image generation Embedding

19 H100 MIG 40GB models

Transcription

Whisper Large V3 (best performance)

V3 - H100 MIG 40GB

Transcription

Whisper Streaming Large v3

H100 MIG 40GB

Transcription

Whisper Streaming Large v3 Turbo

H100 MIG 40GB

Text to speech

Orpheus 3B Websockets

TRT-LLM - H100 MIG 40GB

Text to speech

Orpheus TTS

TRT-LLM - H100 MIG 40GB

Embedding

Qwen3 8B Reranker

BEI - H100 MIG 40GB

Embedding

Qwen3 8B Embedding

BEI - H100 MIG 40GB

Embedding

Tulu 3 8B Reward

V3 - Reward - BEI - H100 MIG 40GB

Embedding

Nomic Embed Code

BEI - H100 MIG 40GB

LLM

Qwen 2.5 7B Math Instruct

2.5 - Math - TRT-LLM - H100 MIG 40GB

LLM

DeepSeek-R1 Qwen 7B

R1 - Qwen - TRT-LLM - H100 MIG 40GB

Transcription

Voxtral Mini 3B

2507 - Mini - H100 MIG 40GB

Image generation

flux-schnell

schnell - bfloat16 - H100 MIG 40GB

LLM

Qwen 2.5 7B Coder Instruct

2.5 - Coder - TRT-LLM - H100 MIG 40GB

LLM

Qwen 2.5 7B Instruct

2.5 - TRT-LLM - H100 MIG 40GB

LLM

Mistral 7B Instruct

v3 - TRT-LLM - H100 MIG 40GB

Transcription

Whisper V3

V3 - H100 MIG 40GB

Image generation

flux-dev

dev - bloat16 - H100 MIG 40GB

Transcription

Whisper V3 Turbo

V3 - Turbo - H100 MIG 40GB

🔥 Trending models

Model API

LLM

GPT OSS 120B

MoE

LLM

GPT OSS 20B

MoE

Image generation

Qwen Image

Text-to-Image

Text to speech

Orpheus TTS

TRT-LLM - H100 MIG 40GB

Explore Baseten today

Start deploying

Talk to an engineer