Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
Vicuna · Ollama
Search for models on Ollama.
  • vicuna

    General use chat model based on Llama and Llama 2 with 2K to 16K context sizes.

    7b 13b 33b

    1.2M  Pulls 111  Tags Updated  2 years ago

  • llava

    🌋 LLaVA is a novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding. Updated to version 1.6.

    vision 7b 13b 34b

    15M  Pulls 98  Tags Updated  2 years ago

  • wizard-vicuna-uncensored

    Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford.

    7b 13b 30b

    1.3M  Pulls 49  Tags Updated  2 years ago

  • wizard-vicuna

    Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.

    13b

    522.6K  Pulls 17  Tags Updated  2 years ago

  • granite3.2-vision

    A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.

    vision tools 2b

    1M  Pulls 5  Tags Updated  1 year ago

  • AgentricAi/AgentricAI_LLaVa

    is a novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding.

    vision

    148  Pulls 1  Tag Updated  1 year ago

  • laff0505/magicienVicunaNonCensured

    ollama run wizard-vicuna-uncensored

    tools

    1  Pull 1  Tag Updated  6 days ago

  • tungqv/COCA

    This is a Vietnamese language model capable of mastering Vietnamese and understanding Vietnamese. It can serve as a content writer, advertising copywriter, giving ideas, answer based on source,...

    95  Pulls 1  Tag Updated  1 year ago

  • bdx0/vietcuna

    3b 7b

    87  Pulls 5  Tags Updated  2 years ago

  • vanilj/reflection-70b-iq2_xxs

    Reflection Llama-3.1 70B is (currently) the world's top open-source LLM, trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course.

    350  Pulls 1  Tag Updated  2 years ago

  • ImOmkar/Vidwan

    Vidwan is a customized AI model based on LLaMA 3, designed to provide academic and research-based responses. It specializes in assisting with complex topics, answering in-depth questions, and providing structured insights.

    tools

    81  Pulls 1  Tag Updated  1 year ago

  • ahmadwaqar/smolvlm2-256m-video

    Ultra-compact 256M vision-language model for video/image understanding. Supports visual QA, captioning, OCR, video analysis. Only 1.38GB VRAM. Built on SigLIP + SmolLM2. Available in Q8 and FP16. Apache 2.0 license.

    vision

    1,472  Pulls 2  Tags Updated  7 months ago

  • ahmadwaqar/smolvlm2-agentic-gui

    Lightweight 2.2B vision model for GUI automation - clicks, types, scrolls on screenshots. Fine-tuned for agentic reasoning with normalized [0,1] coordinate output. Available in Q4_K_M, Q8_0, and FP16 quantizations. Apache 2.0 license.

    vision

    560  Pulls 3  Tags Updated  7 months ago

  • huihui_ai/granite3.2-vision-abliterated

    A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.

    vision tools 2b

    7,942  Pulls 5  Tags Updated  1 year ago

  • rafw007/qwen3.8-27b-redteam

    Verified configuration + measured results for abliterated (uncensored) Qwen3.8-27B running as an autonomous redteam/sysadmin agent, served via llama-swap. This card documents OUR tested configuration and results on live tasks

    282  Pulls 1  Tag Updated  2 days ago

  • ahmadwaqar/smolvlm2-500m-video

    Compact 500M vision-language model for video/image understanding. Supports visual QA, captioning, OCR, video analysis. Only 1.8GB VRAM. Built on SigLIP + SmolLM2. Available in Q8 and FP16. Apache 2.0 license.

    vision

    1,081  Pulls 3  Tags Updated  8 months ago

  • vnd3200/QwQ-LCoT-Instruct

    The QwQ-LCoT-Instruct is a fine-tuned language model designed for advanced reasoning and instruction-following tasks. It leverages the Qwen2.5 base model and has been fine-tuned on the amphora/QwQ-LongCoT-130K dataset, focusing on chain-of-thought (

    tools 3b 7b

    198  Pulls 2  Tags Updated  1 year ago

  • ahmadwaqar/holo-3.1

    Holo-3.1 vision-language computer-use agents by H Company. Locate UI elements and drive web, desktop & mobile automation from a screenshot — returns clicks in normalized [0,1000] coords. 0.8B & 4B, instruct & thinking variants, Q4_K_M/Q8_0. Apache 2.0.

    vision tools 0.8b 4b

    1,195  Pulls 7  Tags Updated  3 months ago

  • os-w/open-assistans-v3-coder

    This is an AI model based on the Gemma4 Model Family, but designed to address issues such as sycophancy or unnecessary praise that may arise in AI models. (It has the ability to reason.) This has no connection to the OpenAssistans project.

    vision tools thinking e2b e4b 12b 26b 31b

    97  Pulls 6  Tags Updated  2 months ago

  • os-w/open-assistans-v3-reasoning

    This is an AI model based on the Gemma4 Model Family, but designed to address issues such as sycophancy or unnecessary praise that may arise in AI models. (It has the ability to reason.) This has no connection to the OpenAssistans project.

    vision tools thinking e2b e4b 12b 26b 31b

    25  Pulls 6  Tags Updated  2 months ago

© 2026 Ollama
Blog Support