Gpt Oss 20B · Ollama

gpt-oss-safeguard

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

153.7K Pulls 3 Tags Updated 10 months 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

sullyvanpontiff/gptsum

Abstractive summarization using gpt-oss-20B as base model.

tools thinking

29 Pulls 1 Tag 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

363 Pulls 4 Tags Updated 6 days 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

639 Pulls 1 Tag Updated 7 months ago

CYLI310/CodeGPT

Code assistant trained by GPT-OSS 20B

tools

236 Pulls 1 Tag Updated 12 months ago

mirage335/gpt-oss-20b-virtuoso

Generic all purpose model. Occasionally may have notable logic, usually Llama-3_3-Nemotron-Super-49B-v1_5 is preferred.

tools thinking

125 Pulls 1 Tag Updated 9 months ago

hardrave/zombiellm

ZombieLLM - a reanimated GPT-2 XL (1.5B) distilled from OpenAI’s GPT-OSS-20B - witty, survival-flavored, and fast. Single-turn by design: the template only feeds the last user message to the model, so each question is a fresh conversation.

86 Pulls 1 Tag Updated 11 months ago