Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
Nemotron · Ollama
Search for models on Ollama.
  • nemotron-3.5-lightning

    NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for always-on agents.

    tools thinking 30b

    28.8K  Pulls 11  Tags Updated  4 days ago

  • nemotron-3-super

    NVIDIA Nemotron 3 Super is a 120B open MoE model activating just 12B parameters to deliver maximum compute efficiency and accuracy for complex multi-agent applications.

    tools thinking cloud 120b

    2.9M  Pulls 7  Tags Updated  5 months ago

  • nemotron3

    NVIDIA Nemotron 3 Nano Omni is a multimodal large language model that unifies video, audio, image, and text understanding to support enterprise-grade Q&A, summarization, transcription, and document intelligence workflows.

    vision tools thinking 33b

    643.4K  Pulls 4  Tags Updated  3 months ago

  • nemotron-cascade-2

    An open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.

    tools thinking 30b

    141.5K  Pulls 3  Tags Updated  4 months ago

  • nemotron-3-ultra

    NVIDIA Nemotron 3 Ultra is built for high-throughput reasoning and long-running agent workflows.

    tools thinking cloud

    48.8K  Pulls 1  Tag Updated  2 months ago

  • nemotron-3-nano

    Nemotron-3-Nano is a new Standard for Efficient, Open, and Intelligent Agentic Models, now updated with a 4B parameter count model.

    tools thinking cloud 4b 30b

    690.2K  Pulls 9  Tags Updated  5 months ago

  • nemotron-mini

    A commercial-friendly small language model by NVIDIA optimized for roleplay, RAG QA, and function calling.

    tools 4b

    699.2K  Pulls 17  Tags Updated  1 year ago

  • nemotron

    Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA to improve the helpfulness of LLM generated responses to user queries.

    tools 70b

    607.3K  Pulls 17  Tags Updated  1 year ago

  • glm-5.1

    GLM-5.1 is our next-generation flagship model for agentic engineering, with significantly stronger coding capabilities than its predecessor. It achieves state-of-the-art performance on SWE-Bench Pro and leads GLM-5 by a wide margin.

    tools thinking cloud

    2.3M  Pulls 1  Tag Updated  4 months ago

  • olmo2

    OLMo 2 is a new family of 7B and 13B models trained on up to 5T tokens. These models are on par with or better than equivalently sized fully open models, and competitive with open-weight models such as Llama 3.1 on English academic benchmarks.

    7b 13b

    3.7M  Pulls 9  Tags Updated  1 year ago

  • bvassie/nemotron-3.5-lightning

    NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for always-on agents.

    8  Pulls 1  Tag Updated  yesterday

  • edtorre/lightning-agent

    Lightning Agent — a 32.9B Nemotron MoE model tuned for Hermes agentic workflows.

    2  Pulls 1  Tag Updated  yesterday

  • brnpistone/NVIDIA-Nemotron-3-Nano-30-AgentCoder-q5-k-m

    tools thinking

    22  Pulls 1  Tag Updated  2 weeks ago

  • nexusriot/Nemotron3-Nano-4B-Uncensored-HauhauCS-Aggressive

    924  Pulls 1  Tag Updated  4 months ago

  • samuser3/NVIDIA-Nemotron-3-Nano-4B

    samuser3/NVIDIA-Nemotron-3-Nano-4B is a quantized (Q4_K_M) small language model by NVIDIA, designed for edge deployment with strong reasoning, coding and friendly responses, suitable for local AI tasks like voice assistants and gaming NPCs.

    425  Pulls 1  Tag Updated  4 months ago

  • kaylee12102/NVIDIA-Nemotron-3-Nano-4B-GGUF

    48  Pulls 1  Tag Updated  3 months ago

  • gag0/Nemotron-Cascade-2-30B-A3B

    tools thinking

    36  Pulls 1  Tag Updated  4 months ago

  • mirage335/NVIDIA-Nemotron-Nano-9B-v2-virtuoso

    1,331  Pulls 1  Tag Updated  7 months ago

  • hung_alex/Nemotron-Content-Safety-Reasoning-4B

    https://huggingface.co/nvidia/Nemotron-Content-Safety-Reasoning-4B

    24  Pulls 2  Tags Updated  4 months ago

  • mirage335/Nemotron-3-Nano-30B-A3B-virtuoso

    Possibly useful for agentic AI systems. Apparently compatible with ~16GB VRAM .

    tools

    828  Pulls 1  Tag Updated  7 months ago

© 2026 Ollama
Blog Contact