Skip to main content
NVIDIA
Explore
Models
Skills
Blueprints
GPUs
Docs
ForumsSupport
Terms of Use
Privacy Policy
Your Privacy Choices
Contact

Copyright © 2026 NVIDIA Corporation

Models

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

Optimized by NVIDIALaunch from Hugging FaceBeta

Filters (1)

Use Case
Inference Providers
Publisher
NIM Container GPUs
Labels (1)
6 models
NVIDIA
DownloadableFree Endpoint

nemotron-3-ultra-550b-a55b

Open, efficient hybrid Mamba-Transformer MoE with 1M context, excelling in agentic reasoning, coding, planning, tool calling, and more
Agent
MoEFrontierReasoningLong Context
Items per page
of 1 pages
52M API calls in the last 30 days
Last updated on June 4, 2026
DeepSeek AI
DownloadableFree Endpoint

deepseek-v4-flash

DeepSeek V4 Flash is a 284B MoE model with 1M-token context optimized for fast coding and agents.
MoE
codingfastagentic
15M API calls in the last 30 days
Last updated on April 24, 2026
DeepSeek AI
DownloadableFree Endpoint

deepseek-v4-pro

DeepSeek V4 scales to 1M-token context windows with efficient MoE architecture for coding tasks.
Moe
reasoningcodingagentic
8M API calls in the last 30 days
Last updated on April 24, 2026
NVIDIA
DownloadableFree Endpoint

nemotron-3-super-120b-a12b

Open, efficient hybrid Mamba-Transformer MoE with 1M context, excelling in agentic reasoning, coding, planning, tool calling, and more
MoE
ReasoningChatLong ContextInstruction Following
60M API calls in the last 30 days
Last updated on March 11, 2026
Qwen
DownloadableFree Endpoint

qwen3.5-397b-a17b

Next-gen Qwen 3.5 VLM (400B MoE) brings advanced vision, chat, RAG, and agentic capabilities.
MoE
image-to-imageVLMagentic
16M API calls in the last 30 days
Last updated on February 16, 2026
NVIDIA
DownloadableFree Endpoint

nemotron-3-nano-30b-a3b

Open, efficient MoE model with 1M context, excelling in coding, reasoning, instruction following, tool calling, and more
MoE
ReasoningLong ContextInstruction Following
12M API calls in the last 30 days
Last updated on December 15, 2025