Skip to main content

Your Privacy Choices

Copyright © 2026 NVIDIA Corporation

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 Endpoint3

Partner Endpoint3

Download Available3

Use Case

Drug Discovery0Retrieval Augmented Generation0Image-to-Text0Speech-to-Text0Image Generation0

Inference Providers

Deepinfra3OpenRouter3GMI Cloud3Together AI2Lightning AI1

Publisher

DeepSeek AI2Qwen1NVIDIA0Meta0Google0

NIM Container GPUs

H100 80GB HBM31B2001H2001A100 SXM4 80GB0L40S0

Labels (2)

MoEagentic

3 models

Sort By

DownloadableFree Endpoint

deepseek-v4-flash

DeepSeek V4 Flash is a 284B MoE model with 1M-token context optimized for fast coding and agents.

coding fast agentic

Items per page

of 1 pages

15M API calls in the last 30 days

Last updated on April 24, 2026

DownloadableFree Endpoint

deepseek-v4-pro

DeepSeek V4 scales to 1M-token context windows with efficient MoE architecture for coding tasks.

reasoning coding agentic

8M API calls in the last 30 days

Last updated on April 24, 2026

DownloadableFree Endpoint

qwen3.5-397b-a17b

Next-gen Qwen 3.5 VLM (400B MoE) brings advanced vision, chat, RAG, and agentic capabilities.

image-to-image VLM agentic

16M API calls in the last 30 days

Last updated on February 16, 2026