Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
Kimi · Ollama
Search for models on Ollama.
  • kimi-k2.5

    Kimi K2.5 is an open-source, native multimodal agentic model that seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.

    vision tools thinking cloud

    241.5K  Pulls 1  Tag Updated  2 months ago

  • kimi-k2-thinking

    Kimi K2 Thinking, Moonshot AI's best open-source thinking model.

    tools thinking cloud

    54.5K  Pulls 1  Tag Updated  5 months ago

  • kimi-k2

    A state-of-the-art mixture-of-experts (MoE) language model. Kimi K2-Instruct-0905 demonstrates significant improvements in performance on public benchmarks and real-world coding agent tasks.

    tools cloud

    60K  Pulls 1  Tag Updated  6 months ago

  • granite3.3

    IBM Granite 2B and 8B models are 128K context length language models that have been fine-tuned for improved reasoning and instruction-following capabilities.

    tools 2b 8b

    990.2K  Pulls 3  Tags Updated  12 months ago

  • KimiDandy/kaizenv10

    tools

    507  Pulls 1  Tag Updated  1 year ago

  • KimiDandy/kaizenspeaking

    52  Pulls 1  Tag Updated  1 year ago

  • KimiDandy/llm4090

    14  Pulls 1  Tag Updated  1 year ago

  • KimiDandy/kaizenv8

    tools

    12  Pulls 1  Tag Updated  1 year ago

  • KimiDandy/kaizenv9

    tools

    10  Pulls 1  Tag Updated  1 year ago

  • KimiDandy/kaizenv6

    4  Pulls 1  Tag Updated  1 year ago

  • KimiDandy/kaizenv1

    4  Pulls 1  Tag Updated  1 year ago

  • KimiDandy/kaizenv7

    3  Pulls 1  Tag Updated  1 year ago

  • KimiDandy/kaizenv5

    2  Pulls 1  Tag Updated  1 year ago

  • KimiDandy/kaizenv2

    2  Pulls 1  Tag Updated  1 year ago

  • KimiDandy/kaizenv4

    1  Pull 1  Tag Updated  1 year ago

  • KimiDandy/llm4070

    1  Pull 1  Tag Updated  1 year ago

  • KimiDandy/kaizenv3

    1  Tag Updated  1 year ago

  • eliandro/Kimily

    tools

    3  Pulls 1  Tag Updated  5 days ago

  • hadad/qwen3-4bd

    Qwen3 fine-tuned using an ultra massive distilled dataset derived from a range of powerful AI models, including Kimi K2.5, Qwen 3.5, Claude Opus 4.6, Claude Opus 4.5, Gemini 3 Pro, Claude Haiku 4.5, GPT 5.2, Gemini 3.1 Pro, GLM 4.7, GLM 5 .......

    tools thinking

    126  Pulls 2  Tags Updated  1 week ago

  • huihui_ai/kimi-k2-abliterated

    A state-of-the-art mixture-of-experts (MoE) language model. Kimi K2-Instruct-0905 demonstrates significant improvements in performance on public benchmarks and real-world coding agent tasks.

    tools 1026b

    609  Pulls 6  Tags Updated  3 months ago

© 2026 Ollama
Blog Contact