Model library

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

11 vLLM models

OpenBMB Logo
Text to speech

VoxCPM2

vLLM - H100
Qwen Logo
LLM

Qwen3.5 35B-A3B

V1 - Latency - vLLM - H100
Qwen Logo
LLM

Qwen3.5 122B-A10B

V1 - Latency - vLLM - H100
Qwen Logo
LLM

Qwen3.5 9B

V1 - Latency - vLLM - H100
Qwen Logo
LLM

Qwen3.5 4B

V1 - Latency - vLLM - H100
Mistral AI logo
LLM

Mistral Small 3.1

3.1 - vLLM - H100
Qwen Logo
Text to speech

Qwen3 TTS 12Hz

TTS - vLLM - H100
Stepfun logo icon
LLM

Step 3.7 Flash

3.7 - FP8 - vLLM - H100
Meta AI logo
LLM

Llama 4 Maverick

V4.0 - Instruct - vLLM - B200
Meta AI logo
LLM

Llama 4 Scout

V4.0 - Instruct - vLLM - H100

🔥 Trending models