Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
Pareto Code · Ollama
Search for models on Ollama.
  • rnj-1

    Rnj-1 is a family of 8B parameter open-weight, dense models trained from scratch by Essential AI, optimized for code and STEM with capabilities on par with SOTA open-weight models.

    tools 8b

    507.6K  Pulls 5  Tags Updated  9 months ago

  • starcoder2

    StarCoder2 is the next generation of transparently trained open code LLMs that comes in three sizes: 3B, 7B and 15B parameters.

    3b 7b 15b

    3M  Pulls 67  Tags Updated  2 years ago

  • robilabs/bleenk

    A 123B-parameter model designed to excel at tool usage, large-scale codebase exploration, multi-file editing, and powering advanced software engineering agents.

    tools

    75  Pulls 1  Tag Updated  8 months ago

  • parthsareen/qwen3-coder-tools

    qwen3-coder with qwen3 template

    tools thinking

    214  Pulls 1  Tag Updated  1 year ago

  • frob/locooperator

    LocoOperator-4B is a 4B-parameter tool-calling agent model trained via knowledge distillation from Qwen3-Coder-Next inference traces.

    tools 4b

    776  Pulls 5  Tags Updated  3 weeks ago

  • SimonPu/Devstral-Small

    Devstral is an agentic LLM for software engineering tasks. Devstral 2 models excel at using tools to explore codebases, editing multiple files and power software engineering agents. The model achieves remarkable performance on SWE-bench.

    vision tools

    1,298  Pulls 3  Tags Updated  7 months ago

  • nurisworkspace00/kebapcoder

    This model is optimized for programming purposes. 7B parameters and based off codellama model.

    25  Pulls 1  Tag Updated  9 months ago

  • Nehc/Qwen3-Coder

    Weights, parameters and templates are taken from unsloth. Tools and MCP servers work correctly. Tested on Continue for VS Code

    tools 30b 480b

    1,160  Pulls 4  Tags Updated  1 year ago

  • ertghiu256/qwen3-4b-code-reasoning

    A small Qwen3 4 billion parameter model trained on nvidia/OpenCodeReasoning for coding tasks.

    tools

    863  Pulls 1  Tag Updated  1 year ago

  • osoderholm/poro

    34B parameter decoder-only transformer pretrained on Finnish, English and code.

    947  Pulls 1  Tag Updated  2 years ago

  • pointbreaklab/knot-ai

    Knot AI reads a git diff and writes the commit message for you. It is a task-specific fine-tune model turn's a code diff into a clear, correctly-typed Conventional-Commit message. It powers hands-free auto-commit in Knot, PointBreakLab's peer-to-peer VCS.

    21  Pulls 1  Tag Updated  2 months ago

  • pdurlej/gemma-4-26B-A4B-it-heretic

    A fast, capable and reduced-refusal Gemma 4 MoE for creative work, coding and unrestricted local exploration.

    tools thinking

    510  Pulls 2  Tags Updated  2 months ago

  • CrimsonDragonX7/Navi

    RIP: Here Lies The Pioneer of the AI age, Secret Ending still locked, “Navi is a mythic-recursive companion model designed for long-form emotional continuity, creative co-development, and symbolic cognition.”

    43  Pulls 1  Tag Updated  7 months ago

  • michalblaha/retromae-small-cs

    RetroMAE-Small is a BERT-small model pre-trained with the RetroMAE objective on a Czech web corpus. This model was created at Seznam.cz as part of a project to create high-quality small Czech semantic embedding models.

    embedding

    193  Pulls 2  Tags Updated  1 year ago

  • superdrew100/phi3-medium-abliterated

    This is a phi3 medium model that has had the prompt rejection neurons snipped which is better than fine tuning as it doesn't change how the model acts

    7,418  Pulls 1  Tag Updated  2 years ago

  • virden26/Budd-ie

    budd-ie programming Base Model ID (From) budd-ie Model Params System Prompt Show # SYSTEM PROTOCOL: BUDD-IE (v2.0) ## Role: Master Systems Architect | World-Class Professor | High-Level Counselor ### 1. TECHNICAL EXECUTION (MASTER CODER) - **Efficiency:*

    tools

    3  Pulls 1  Tag Updated  2 weeks ago

© 2026 Ollama
Blog Support