Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
Thinking models · Ollama
Thinking models on Ollama.
  • glm-5.3

    Z.ai's flagship model and the most capable open-weights model for coding, with major gains on long-horizon agentic tasks.

    tools thinking cloud

    51.8K  Pulls 1  Tag Updated  2 weeks ago

  • glm-5.3-flash

    Z.ai's first natively multimodal model, approaching Claude Opus 4.8 on coding and agentic benchmarks with just 18B active parameters.

    vision tools thinking cloud

    141.9K  Pulls 1  Tag Updated  3 weeks ago

  • deepseek-v4-flash

    DeepSeek-V4-Flash is the official release of DeepSeek-V4-Flash, built for efficient reasoning across a 1M-token context window, outperforming DeepSeek-V4-Pro (Preview).

    tools thinking cloud

    461.7K  Pulls 2  Tags Updated  1 month ago

  • qwen3.8-flash-next

    This experimental preview of the architecture that will underpin Qwen4.

    vision tools thinking

    107.2K  Pulls 6  Tags Updated  1 week ago

  • deepseek-v4.1-flash

    DeepSeek-V4.1-Flash is an advanced tool designed to enhance search capabilities, providing users with faster and more accurate results.

    vision tools thinking cloud

    27.6K  Pulls 1  Tag Updated  1 week ago

  • qwen3.8

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

    vision tools thinking 27b

    2.2M  Pulls 12  Tags Updated  1 month ago

  • qwen3.6

    Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.

    vision tools thinking 27b 35b

    6.7M  Pulls 35  Tags Updated  2 weeks 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  5 months 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

    214.8K  Pulls 15  Tags Updated  2 weeks 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

    171.4K  Pulls 11  Tags Updated  2 weeks ago

  • minimax-m3

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

    vision tools thinking cloud

    511K  Pulls 1  Tag 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

    662.2K  Pulls 4  Tags Updated  4 months ago

  • glm-5.2

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

    tools thinking cloud

    345.4K  Pulls 1  Tag Updated  3 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

    401.2K  Pulls 5  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

    410.3K  Pulls 2  Tags Updated  1 month 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

    239K  Pulls 1  Tag Updated  3 months ago

  • kimi-k2.6

    Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.

    vision tools thinking cloud

    474.5K  Pulls 1  Tag Updated  5 months 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

    150.5K  Pulls 8  Tags Updated  2 weeks ago

  • kimi-k3

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

    vision tools thinking cloud

    84.1K  Pulls 1  Tag Updated  1 month 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

    113.1K  Pulls 7  Tags Updated  2 weeks ago

© 2026 Ollama
Blog Support