Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
lam · Ollama
Search for models on Ollama.
  • laguna-s-2.1

    Our most capable model to date, designed for long-horizon work. 70.2% on Terminal-Bench 2.1 at 118B-A8B.

    tools thinking

    129.5K  Pulls 8  Tags Updated  1 week ago

  • laguna-xs-2.1

    Laguna XS 2.1 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine.

    tools thinking

    106.2K  Pulls 7  Tags Updated  6 days ago

  • laguna-xs.2

    Laguna XS.2 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine.

    tools thinking

    28.6K  Pulls 7  Tags Updated  1 month ago

  • llama3-gradient

    This model extends LLama-3 8B's context length from 8k to over 1m tokens.

    8b 70b

    1M  Pulls 35  Tags Updated  2 years ago

  • lfm2.5

    LFM2.5-8B-A1B, an edge model built for fast, reliable tool calling on consumer hardware.

    tools thinking 8b

    140.3K  Pulls 5  Tags Updated  3 months ago

  • lfm2

    LFM2 is a family of hybrid models designed for on-device deployment. LFM2-24B-A2B is the largest model in the family, scaling the architecture to 24 billion parameters while keeping inference efficient.

    tools 24b

    1.1M  Pulls 6  Tags Updated  6 months ago

  • llama3.1

    Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.

    tools 8b 70b 405b

    119.2M  Pulls 93  Tags Updated  1 year ago

  • llama3.3

    New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model.

    tools 70b

    4.1M  Pulls 14  Tags Updated  1 year ago

  • muse-glimmer

    Meta's latest open model built for always-on local agents. 30B parameters, licensed under Apache 2.0 and runs on a single GPU — tuned for tool use, long tasks, and failure recovery.

    vision tools thinking 30b

    191.9K  Pulls 15  Tags Updated  1 week 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

    656.9K  Pulls 4  Tags Updated  4 months ago

  • deepseek-v4-pro

    DeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a large context window and three reasoning modes.

    tools thinking cloud

    385.7K  Pulls 2  Tags Updated  3 weeks ago

  • qwen3-vl

    The most powerful vision-language model in the Qwen model family to date.

    vision tools thinking 2b 4b 8b 30b 32b 235b

    5.8M  Pulls 57  Tags Updated  10 months ago

  • lfm2.5-thinking

    LFM2.5 is a new family of hybrid models designed for on-device deployment.

    tools thinking 1.2b

    1.3M  Pulls 5  Tags Updated  7 months ago

  • deepseek-ocr

    DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.

    vision 3b

    527.7K  Pulls 3  Tags Updated  9 months ago

  • olmo-3

    Olmo is a series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets.

    tools thinking 7b 32b

    455.5K  Pulls 15  Tags Updated  8 months ago

  • olmo-3.1

    Olmo is a series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets.

    tools thinking 32b

    288.8K  Pulls 10  Tags Updated  8 months ago

  • mistral-large-3

    A general-purpose multimodal mixture-of-experts model for production-grade tasks and enterprise workloads.

    vision tools cloud

    102.6K  Pulls 1  Tag Updated  9 months ago

  • llama3.2

    Meta's Llama 3.2 goes small with 1B and 3B models.

    tools 1b 3b

    82.6M  Pulls 63  Tags Updated  1 year ago

  • qwen3

    Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.

    tools thinking 0.6b 1.7b 4b 8b 14b 30b 32b 235b

    36.4M  Pulls 58  Tags Updated  11 months ago

  • qwen2.5

    Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has multilingual support.

    tools 0.5b 1.5b 3b 7b 14b 32b 72b

    39.5M  Pulls 133  Tags Updated  1 year ago

© 2026 Ollama
Blog Support