Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
qwen2 · Ollama
Search for models on Ollama.
  • qwen2.5

    Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has multilingual support.

    tools 0.5b 1.5b 3b 7b 14b 32b 72b

    32M  Pulls 133  Tags Updated  1 year ago

  • qwen2.5-coder

    The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.

    tools 0.5b 1.5b 3b 7b 14b 32b

    16.3M  Pulls 199  Tags Updated  1 year ago

  • qwen2

    Qwen2 is a new series of large language models from Alibaba group

    tools 0.5b 1.5b 7b 72b

    5.9M  Pulls 97  Tags Updated  1 year ago

  • qwen2.5vl

    Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL.

    vision 3b 7b 32b 72b

    2.2M  Pulls 17  Tags Updated  1 year ago

  • qwen2-math

    Qwen2 Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of open-source models and even closed-source models (e.g., GPT4o).

    1.5b 7b 72b

    1M  Pulls 52  Tags Updated  1 year ago

  • smallthinker

    A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model.

    3b

    247.3K  Pulls 5  Tags Updated  1 year ago

  • cieloforge/qwen2.5-coder-7b-instruct-spec

    A custom model of Qwen2.5-coder:7B-Instruct with the Qwen2.5-coder:3B-instruct used as a speculative fill model to speed up inference. Primarily made for TabbyML Usage.

    tools

    541  Pulls 1  Tag Updated  3 weeks ago

  • cieloforge/qwen2.5-14B-instruct-spec

    A Custom Qwen2.5-coder:14B-instruct model using a Qwen2.5-coder:3B-instruct model for Speculative Fill. Primary usage is for TabbyML.

    tools

    262  Pulls 1  Tag Updated  3 weeks ago

  • jarvis-tech/Jarvis_Distilled_v1

    A lightweight distilled Qwen2.5-based local model tuned for fast inference, general-purpose chat, and efficient on-device use. Good for everyday assistance, concise reasoning, and low-footprint deployments.

    tools

    76  Pulls 1  Tag Updated  1 week ago

  • benjaminjodom45/qwen25coder3b

    FROM ./Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf TEMPLATE """{{ .Prompt }}""" PARAMETER temperature 0.4 PARAMETER top_p 0.9 PARAMETER top_k 40 PARAMETER repeat_penalty 1.15 PARAMETER mirostat 2 PARAMETER mirostat_eta 0.2 PARAMETER mirostat_tau 5.0 PARAMETER

    tools

    81  Pulls 1  Tag Updated  2 weeks ago

  • miti99/gte-qwen2

    https://huggingface.co/Alibaba-NLP/gte-Qwen2-1.5B-instruct

    18.5K  Pulls 1  Tag Updated  2 months ago

  • cieloforge/qwen2.5-coder-3b-instruct-spec

    A Custom Qwen2.5-coder:3b-instruct using a Qwen2.5-coder:1.5b model as speculative fill. Primary usage for this model is TabbyML.

    tools

    76  Pulls 1  Tag Updated  3 weeks ago

  • junquan2k/Qwen2.5-VL-7B-local9-0414

    vision

    38  Pulls 1  Tag Updated  2 weeks ago

  • code-forge-temple/agentic-signal-qwen2.5-coder

    This model has been finetuned with data from Agentic Signal (a visual AI agent workflow automation platform with local LLM integration).

    7b

    36  Pulls 1  Tag Updated  2 weeks ago

  • qcwind/qwen2.5-7B-instruct-Q4_K_M

    qwen2.5-7B-instruct-Q4_K_M

    tools

    4,896  Pulls 1  Tag Updated  3 months ago

  • sssonusharma1999/ankit-coder

    A concise, root-cause-first coding assistant built on Qwen2.5-Coder 7B. Debug and generate code with zero filler — runs entirely locally via Ollama.

    26  Pulls 1  Tag Updated  1 week ago

  • r4c3r/qwen2.5-3b-heretic

    Fully decensored Qwen2.5-3B-Instruct processed with Heretic abliteration. Achieves 3/100 refusals with 0.11 KL divergence — 97% censorship removal on a consumer RTX 4060. GGUF format, ready to run.

    986  Pulls 1  Tag Updated  2 weeks ago

  • quantumcookie/Sakura-qwen2.5-v1.0

    日语汉化翻译LLM

    1.5b 7b 14b

    1,498  Pulls 3  Tags Updated  5 months ago

  • r4c3r/qwen2.5-coder-3b-heretic

    Fully decensored Qwen2.5-Coder-3B-Instruct processed with Heretic abliteration. Achieves 3/100 refusals with an exceptionally low KL divergence of 0.0163 — near-zero model degradation on a consumer RTX 4060.

    777  Pulls 1  Tag Updated  2 weeks ago

  • novaforgeai/qwen2.5

    NovaForge AI – Qwen 2.5-3B Optimized A CPU-optimized, lightweight, general-purpose AI model built on Qwen 2.5-3B, designed for fast and private local inference on low-resource systems.

    tools

    1,068  Pulls 1  Tag Updated  5 months ago

© 2026 Ollama
Blog Contact