Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
Ollama
Search for models on Ollama.
  • ornith-1.5

    Chirp Chirp! 🐦 We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement.

    vision 9b 35b 397b

    31.6K  Pulls 3  Tags Updated  5 days ago

  • qwen3.8

    Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks.

    vision tools thinking 27b

    733.1K  Pulls 12  Tags Updated  1 week ago

  • 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

    132K  Pulls 11  Tags Updated  1 week 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

    163K  Pulls 15  Tags Updated  1 week ago

  • kimi-k3

    Kimi K3 is an open-weight, native multimodal agentic model and our most capable model to date.

    vision tools thinking cloud

    53.2K  Pulls 1  Tag Updated  4 weeks ago

  • 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

    104.3K  Pulls 7  Tags Updated  4 days 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

    97.7K  Pulls 7  Tags Updated  4 days ago

  • ornith

    A self-improving family of open-source models for agentic coding

    tools 9b 35b

    415.5K  Pulls 9  Tags Updated  1 month ago

  • north-mini-code-1.0

    North Mini Code is Cohere's first model for developers — a 30B Mixture-of-Experts model with 3B active parameters, built for agentic software engineering.

    tools thinking

    45K  Pulls 7  Tags Updated  2 months ago

  • glm-5.2

    GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks.

    tools thinking cloud

    329.1K  Pulls 1  Tag Updated  2 months ago

  • kimi-k2.7-code

    Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built upon Kimi K2.6, with substantial improvements on real-world long-horizon coding tasks and roughly 30% lower thinking-token usage.

    vision tools thinking cloud

    223.8K  Pulls 1  Tag Updated  2 months ago

  • nemotron-3-ultra

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

    tools thinking cloud

    57.5K  Pulls 1  Tag Updated  2 months ago

  • lfm2.5

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

    tools thinking 8b

    125.9K  Pulls 5  Tags Updated  2 months ago

  • minimax-m3

    MiniMax M3: Coding & Agentic Frontier. 1M context window. Native Multimodality.

    vision tools thinking cloud

    471.4K  Pulls 1  Tag Updated  2 months ago

  • minicpm-v4.5

    A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone

    vision 8b

    29.9K  Pulls 13  Tags Updated  2 months ago

  • minicpm-v4.6

    A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

    vision 1b

    37.9K  Pulls 13  Tags Updated  2 months ago

  • granite4.1-guardian

    Granite Guardian 4.1 is a specialized safety and judging model from IBM Research that evaluates whether LLM prompts and responses meet specified harm criteria.

    tools thinking 8b

    11.6K  Pulls 16  Tags Updated  2 months ago

  • mistral-medium-3.5

    Mistral Medium 3.5 is the first flagship model of Mistral AI that merged instruction-following, reasoning, and coding in a single set of 128B weights.

    vision tools thinking 128b

    352.4K  Pulls 5  Tags Updated  3 months ago

  • granite4.1

    IBM Granite Models are a family of enterprise-ready, open foundation models that support multilingual capabilities, coding, retrieval-augmented generation (RAG), tool use, and structured JSON output. Released under Apache 2.0 license.

    tools 3b 8b 30b

    370.5K  Pulls 48  Tags Updated  3 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

    649.7K  Pulls 4  Tags Updated  3 months ago

© 2026 Ollama
Blog Contact