Skip to main content

Models

Deploy and scale models on your GPU infrastructure of choice with NVIDIA NIM inference microservices

Optimized by NVIDIA Launch from Hugging FaceBeta

Filters (2)

Free Endpoint2

Partner Endpoint2

Download Available1

Use Case

Drug Discovery0Image Generation0Speech-to-Text0Text-to-Image0Image-to-Text0

Inference Providers

Deepinfra2OpenRouter2CoreWeave2Together AI1GMI Cloud1

Publisher

NVIDIA1DeepSeek AI1Black forest labs0Meta0Arc0

NIM Container GPUs

A100 SXM4 80GB0DGX Spark0H100 80GB HBM30L40S0

Labels (2)

MoeMultimodal

2 models

Sort By

models

NVIDIA
Free Endpoint
nemotron-3.5-super-vl-120b-a12b
Nemotron 3.5 Super early-access reasoning model for agentic, coding, tool-calling, and multimodal workloads
DeepSeek AI
DownloadableFree Endpoint
deepseek-v4.1-flash
552B MoE, 8B active params with native multimodal support and lower API cost using smaller KV cache

Items per page

of 1 pages

Agent

MoE
Multimodal
Reasoning
Long Context

Last updated on October 15, 2026

Vision Language Model

Multimodal MOE
KV Cache Optimization
Causal Encoder Decoder

Last updated on September 18, 2026

Your Privacy Choices

Copyright © 2026 NVIDIA Corporation