Models
Deploy and scale models on your GPU infrastructure of choice with NVIDIA NIM inference microservices
models
552B MoE, 8B active params with native multimodal support and lower API cost using smaller KV cacheFree Endpointdeepseek-v4.1-flash
StreamPETR offers efficient 3D object detection for autonomous driving by propagating sparse object queries temporally.Free Endpointstreampetr
Record-setting accuracy and performance for Mandarin English transcriptions.Downloadableparakeet-ctc-0.6b-zh-cn
End-to-end autonomous driving stack integrating perception, prediction, and planning with sparse scene representations for efficiency and safety.Free Endpointsparsedrive
Items per page
of 1 pages