Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
gpt oss 20b · Ollama
Search for models on Ollama.
  • gpt-oss-safeguard

    gpt-oss-safeguard-20b and gpt-oss-safeguard-120b are safety reasoning models built-upon gpt-oss

    tools thinking 20b 120b

    154.6K  Pulls 3  Tags Updated  10 months ago

  • pd95/gptoss-mlx

    Experimental MLX-backed GPT-OSS 20B for custom Ollama builds. Requires GptOssForCausalLM support and is not compatible with the regular Ollama app.

    tools thinking 20b

    373  Pulls 4  Tags Updated  1 week ago

  • voytas26/openclaw-oss-20b-deterministic

    Deterministic, tool-aware variant of gpt-oss:20b optimized for OpenClaw. Designed for autonomous agents, strict tool schema adherence, concise outputs, and stable behavior in automation workflows.

    tools thinking

    4,879  Pulls 1  Tag Updated  7 months ago

  • DedeProGames/gpt-oss-nano

    A smaller, experimental model of gpt-oss:20b.

    6b

    616  Pulls 1  Tag Updated  6 months ago

  • emfhal/gpt-oss

    CPU-optimized gpt-oss:20b for Kubernetes and VM environments. Runs without GPU, tuned for predictable CPU inference, balanced quality, and reduced memory usage.

    tools thinking

    641  Pulls 1  Tag Updated  8 months ago

  • DedeProgames/Astral-2.7

    Astral-2.7 is a 20B-parameter AI model based on gpt-oss:20b, designed for high performance on general reasoning tasks.

    tools thinking 20b

    214  Pulls 2  Tags Updated  6 months ago

  • s44t12/chatgpt

    This is just a renamed gpt-oss:20b for a cleaner workflow using the API

    tools thinking

    118  Pulls 1  Tag Updated  11 months ago

  • macdev/gpt-oss20b-large-ctx

    gpt-oss20b-large-ctx

    tools thinking

    48  Pulls 1  Tag Updated  11 months ago

  • laloadrianmorales/gpt-laloss20b

    custom gpt-oss:20b model

    tools thinking

    32  Pulls 1  Tag Updated  11 months ago

  • mcgdj/gpt-oss-6.0b

    A smaller, experimental model of gpt-oss:20b. From https://huggingface.co/AmanPriyanshu/gpt-oss-6.0b-specialized-all-pruned-moe-only-7-experts

    895  Pulls 1  Tag Updated  1 year ago

  • jack1230cml/gpt-oss20b

    tools thinking

    141  Pulls 1  Tag Updated  1 year ago

  • richardyoung/gpt-oss-20b-abliterated

    Abliterated build of OpenAI gpt-oss-20b. Note up front: gpt-oss is highly refusal-robust, so this is a modest reduction, published honestly.

    743  Pulls 2  Tags Updated  2 months ago

  • ducquoc/gpt-oss-sonnet

    GPT-oss 20b distilled with Claude Sonnet 4.6 system prompts and customized params, pretty fast response (medium/high thinking).

    tools thinking

    735  Pulls 1  Tag Updated  3 months ago

  • mrasif/gpt-oss-20b-GGUF

    tools thinking

    172  Pulls 1  Tag Updated  1 month ago

  • second_constantine/gpt-oss-u

    Specialized uncensored quants for new OpenAI 20B MOE - Mixture of Experts Model at 80+ T/S. "HERETIC" method results in a model (quantized Q5_1)

    thinking 20b

    30.2K  Pulls 1  Tag Updated  7 months ago

  • MotherMAE/gpt-oss-20b

    tools

    45  Pulls 1  Tag Updated  1 month ago

  • hherb/gpt-oss-20b-biasbusterV4

    tools thinking

    82  Pulls 1  Tag Updated  5 months ago

  • svjack/gpt-oss-20b-heretic

    tools thinking

    2,898  Pulls 1  Tag Updated  9 months ago

  • hherb/gpt-oss-20b-biasbuster

    tools thinking

    19  Pulls 1  Tag Updated  5 months ago

  • sparksammy/gpt-oss-20b-unsloth

    tools thinking

    380  Pulls 3  Tags Updated  6 months ago

© 2026 Ollama
Blog Support