NVIDIA
Explore
Models
Blueprints
GPUs
Docs
⌘KCtrl+K
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 (2)

  • Free Endpoint
    5
  • Partner Endpoint
    8
  • Download Available
    4
  • Retrieval Augmented Generation
    0
  • Drug Discovery
    0
  • Image-to-Text
    0
  • Code Generation
    0
  • Speech-to-Text
    0
  • Deep Infra
    7
  • Bitdeer AI
    4
  • GMI Cloud
    4
  • Together AI
    3
  • Lightning AI
    2
  • Mistral AI
    2
  • DeepSeek AI
    2
  • Moonshotai
    2
  • Google
    1
  • Z.ai
    1
  • A100 SXM4 80GB
    0
  • B200
    0
  • GB200
    0
  • GH200 144G HBM3e
    0
  • H100 80GB HBM3
    0
  • Reasoning
  • Agentic
    • 9 models
    Mistral AI
    Downloadable

    mistral-medium-3.5-128b

    A high performing model for text generation, coding and agentic use cases
    coding
    2d
    Items per page
    of 1 pages
    69.31K
    DeepSeek AI
    Downloadable

    deepseek-v4-pro

    DeepSeek V4 scales to 1M-token context windows with efficient MoE architecture for coding tasks.
    Moe
    1.62M
    1w
    Z.ai
    Downloadable

    glm-5.1

    GLM-5.1 is a flagship LLM for agentic workflows, coding, and long-horizon reasoning tasks.
    Agentic AI
    5.05M
    2w
    Google
    Downloadable

    gemma-4-31b-it

    Dense 31B model delivering frontier reasoning for coding, agentic workflows, and fine-tuning.
    coding
    4.08M
    4w
    Stepfun-ai
    Free Endpoint

    step-3.5-flash

    200B open-source reasoning engine with sparse MoE powering frontier agentic AI.
    Agentic
    9.1M
    2mo
    Mistral AI
    Deprecation in 10dFree Endpoint

    devstral-2-123b-instruct-2512

    State-of-the-art open code model with deep reasoning, 256k context, and unmatched efficiency.
    coding
    2.56M
    4mo
    DeepSeek AI
    Deprecation in 3dFree Endpoint

    deepseek-v3.1-terminus

    DeepSeek-V3.1: hybrid inference LLM with Think/Non-Think modes, stronger agents, 128K context, strict function calling.
    tool calling
    6.12M
    6mo
    Moonshotai
    Deprecation in 4dFree Endpoint

    kimi-k2-instruct-0905

    Follow-on version of Kimi-K2-Instruct with longer context window and enhanced reasoning capabilities.
    long-context
    8.1M
    7mo
    Moonshotai
    Deprecation in 11dFree Endpoint

    kimi-k2-instruct

    State-of-the-art open mixture-of-experts model with strong reasoning, coding, and agentic capabilities
    coding
    13.5M
    9mo