Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
ale lama · Ollama
Search for models on Ollama.
  • llama3.3

    New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model.

    tools 70b

    3.6M  Pulls 14  Tags Updated  1 year ago

  • wizardlm2

    State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.

    7b 8x22b

    973.7K  Pulls 22  Tags Updated  1 year ago

  • alelopinf/Exceltic_family_rol_level_Llama_3_2_1B_Instruct_bnb_4bit

    tools

    3  Pulls 1  Tag Updated  10 months ago

  • alen_ox/llama_3_fin

    This is the financial Q&A model chat

    38  Pulls 1  Tag Updated  1 year ago

  • alexyu90/new-rubric-Llama3.2-3B

    9  Pulls 1  Tag Updated  1 year ago

  • alexyu90/T3-grader-Llama3.2-3B

    1  Pull 1  Tag Updated  1 year ago

  • alelopinf/Exceltic_sector_discipline_Llama_3_2_1B_Instruct_bnb_4bit

    tools

    1  Tag Updated  10 months ago

  • alelopinf/Exceltic_cv_nocv_Llama_3_2_1B_Instruct_bnb_4bit

    tools

    1  Tag Updated  10 months ago

  • alexyu90/A1A2T3-grader-Llama3.2-3B

    1  Tag Updated  1 year ago

  • alen_ox/model_test_llama_3

    1  Tag Updated  1 year ago

  • aligh4699/heydariAI-persian-embeddings

    This model is an Ollama version of heydariAI-persian-embeddings from Hugging Face. This is fine-tuned version of xlm-roberta-base, specifically trained on a massive corpus of Persian data to create high-quality contextual embedding for Persian usages.

    embedding

    571  Pulls 1  Tag Updated  8 months ago

  • alibayram/doktor-gemma3-12b

    Magibu Model Finetune Eğitimi amacıyla hazırlanmış, çok küçük oranda finetune edilmiş model

    3  Pulls 2  Tags Updated  8 months ago

  • anhledger/answer_7

    Phiên bản số 7 của mô hình LLM đã được finetune trên LLama3 để trả lời các câu hỏi về nhà và nhà thầu bằng tiếng Nhật

    2  Pulls 1  Tag Updated  1 year ago

  • alibayram/hunyuan

    Hunyuan is Tencent’s open-source efficient large language model series, designed for versatile deployment across diverse computational environments.

    0.5b 1.8b 4b 7b

    4,177  Pulls 5  Tags Updated  8 months ago

  • altare/arc-m

    An experimental, small 2B language model by Altare Technologies.

    tools

    14  Pulls 1  Tag Updated  8 months ago

  • alekarap/LLAMA123

    1  Pull 1  Tag Updated  10 months ago

  • edulab/edulab1

    Meet EduLab1, the first educational AI model from Edulab. Designed to assist both learners and educators, EduLab1 makes education more accessible by explaining difficult topics and solving problems in an engaging, easy-to-understand

    tools

    1,083  Pulls 1  Tag Updated  2 days ago

  • akritrimai/Llama-SH-GPT

    SPAM/HAM detection model designed to run even on edge devices based on meta’s Llama 3.2

    tools

    306  Pulls 1  Tag Updated  1 year ago

  • alpernae/qwen2.5-auditor

    qwen2.5-auditor is a local Ollama model wrapper built from qwen2.5-coder and tuned for security-focused code review and static analysis; it adopts a strict “Astra” system persona to act like a security engineer/bug-bounty auditor.

    tools

    160  Pulls 1  Tag Updated  1 month ago

  • ad-informatique/AIgle-1_mistral

    AIgle est un modèle open-source, développé par AD informatique sur la base du modèle Ollama Mistral. Les modèles sont, dans l'ordre du plus petit au plus puissant : small ; fast ; latest ; medium ; large.

    vision tools

    51  Pulls 7  Tags Updated  3 months ago

© 2026 Ollama
Blog Contact