Models

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

Filters (3)

Free Endpoint3

Partner Endpoint2

Download Available3

Use Case

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

Inference Providers

OpenRouter2Deepinfra1Bitdeer1CoreWeave1Digital Ocean1

Publisher

NVIDIA3Meta0Google0Mistral AI0Qwen0

NIM Container GPUs

A100 SXM4 80GB0H100 80GB HBM30L40S0A10G0B2000

Labels (3)

MoeInstruction FollowingLong Context

3 models

Sort By

DownloadableFree Endpoint

Open, efficient hybrid Mamba-Transformer MoE model for reasoning, coding, planning, tool calling, and more

Last updated on July 23, 2026

Items per page

of 1 pages

DownloadableFree Endpoint

Open, efficient hybrid Mamba-Transformer MoE with 1M context, excelling in agentic reasoning, coding, planning, tool calling, and more

65M API calls in the last 30 days

Last updated on March 11, 2026

DownloadableFree Endpoint

Open, efficient MoE model with 1M context, excelling in coding, reasoning, instruction following, tool calling, and more

12M API calls in the last 30 days

Last updated on December 15, 2025