Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
O3 Mini · Ollama
Search for models on Ollama.
  • deepcoder

    DeepCoder is a fully open-Source 14B coder model at O3-mini level, with a 1.5B version also available.

    1.5b 14b

    947.7K  Pulls 9  Tags Updated  1 year ago

  • catsarethebest/qwen2.5-N

    Qwen2.5 0.5B fine-tuned on data distilled from GPT 4.1-Nano, 4o, o3, and o4-mini

    tools

    658  Pulls 1  Tag Updated  1 year ago

  • andiariffin/xbai-o4-q4km

    XBai o4 is a fourth-generation open-source language model that outperforms OpenAI-o3-mini in complex reasoning tasks.

    32.8b

    47  Pulls 1  Tag Updated  1 year ago

  • andiariffin/xbai-o4-bf16

    XBai o4 is a fourth-generation open-source language model that outperforms OpenAI-o3-mini in complex reasoning tasks.

    32.8b

    4  Pulls 1  Tag Updated  1 year ago

  • OpenNix/wazuh-llama-3.1-8B-v1

    LLaMA 3.1 8B Instruct model fine-tuned for advanced Wazuh security log analysis with instruction-following capabilities

    628  Pulls 1  Tag Updated  11 months ago

  • OpenNix/wazuh-llama-3.1-8B-base

    LLaMA 3.1 8B Instruct model fine-tuned for advanced Wazuh security log analysis with instruction-following capabilities.

    101  Pulls 1  Tag Updated  11 months ago

  • omkarjava0103/gpt-oss-mini

    tools

    386  Pulls 1  Tag Updated  1 year ago

  • joeAI/phi3.5

    A quick and dirty ollama model made from https://huggingface.co/lmstudio-community/Phi-3.5-mini-instruct-GGUF

    396  Pulls 1  Tag Updated  2 years ago

  • eurecom-ds/phi-3-mini-4k-socratic

    Lightweight, state-of-the-art model for Socratic interactions (fine tuned from Phi-3-mini-4k).

    344  Pulls 15  Tags Updated  2 years ago

  • aratan/Ornith-1.0-35B-uncensored-GGUF

    Uncesored 27 t/s 8 VRAM Muy bueno para hacking e ingenieria inversa

    vision

    651  Pulls 1  Tag Updated  1 month ago

  • hhao/openbmb-minicpm-llama3-v-2_5

    MiniCPM-V surpasses proprietary models such as GPT-4V, Gemini Pro, Qwen-VL and Claude 3 in overall performance, and support multimodal conversation for over 30 languages.

    vision

    45.9K  Pulls 8  Tags Updated  2 years ago

  • HammerAI/openbmb-minicpm-llama3-v-2_5

    openbmb/MiniCPM-Llama3-V-2_5

    vision

    2,585  Pulls 2  Tags Updated  2 years ago

  • oamazonasgabriel/qwen3.6-35b-a3b

    A memory-efficient model configuration of Qwen3.6-35B-A3B using an upstream imatrix-calibrated IQ4_XS quantization and q4_0 KV cache. Designed for 24 GB VRAM

    tools thinking

    2,022  Pulls 1  Tag Updated  2 months ago

  • aratan/Ornith-1.5-35B-A3B-GGUF

    Rápido y mejor que su version anterior pero no es mejor que "Qwen3.7" ni mejor que Qwen3.8 27b

    vision

    70  Pulls 1  Tag Updated  1 week ago

  • LayOnGGUF/llama3-stheno

    Stheno-v3.2-Zeta I have done a test run with multiple variations of the models, merged back to its base at various weights, different training runs too, and this Sixth iteration is the one I like most.

    8b

    1,362  Pulls 1  Tag Updated  1 year ago

  • KHROTU/titlegemma

    A fine-tuned Gemma 3 270M instruct model specialized in generating short, descriptive titles from the first message of a conversation.

    27  Pulls 1  Tag Updated  2 months ago

  • solaiai/30BCoder

    SOLAI Coder 30B is an AI coding model designed for the SOLAI ecosystem, built to power intelligent software development, code generation, reasoning, and AI agent workflows through local and decentralized compute.

    tools

    592.2K  Pulls 1  Tag Updated  3 weeks ago

  • aisingapore/Qwen-SEA-LION-v4-32B-IT

    Qwen-SEA-LION-v4-32B-IT is a multilingual model which has been pretrained and instruct-tuned for the Southeast Asia region. Developed by AI Singapore and funded by National Research Foundation, Singapore.

    tools thinking

    341  Pulls 3  Tags Updated  10 months ago

  • aiasistentworld/Llama-3.1-8B-Instruct-STO-Master

    The **Llama-3.1-8B-Instruct-STO-Master** is a high-performance fine-tune of Meta's Llama-3.1-8B-Instruct. This model represents the "Master Version" (Model E) of an extensive research project aimed at pushing the boundaries of 8B parameter architectures.

    182  Pulls 1  Tag Updated  7 months ago

  • ImFineThanks/Integrator-1-R1-ZERO-3B

    It is an LLM fine-tuned from Llama-3.2-3B-Instruct, capable of reasoning in the format <reasoning>...</reasoning><answer>...</answer>. Its capability might improve with further training.

    tools

    82  Pulls 1  Tag Updated  1 year ago

© 2026 Ollama
Blog Support