Models

gpt-oss-safeguard

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

reayudbhm/gpt-oss-120b

HammerAI/gpt-oss

openai/gpt-oss-120b

ionicus/kldzj_gpt-oss-120b-heretic-v2-bf16

Bartowski's GGUF at full BF16 weights. Parameters and Template optimized for tool use.

mirage335/gpt-oss-120b-virtuoso

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

zazula/gpt-oss-120b-max

haybu/gpt-oss-120b

hydai/gpt-oss-120b-mandarin-thinking

Converted to MXFP4_MOE from https://huggingface.co/FreeSEED-AI/gpt-oss-120b-mandarin-thinking

hardcore_moore/kiwi-ollama-gpt-oss-120b-64k

hardcore_moore/kiwi-ollama-gpt-oss-120b-32k

optimistic_mcnulty_933/gpt-oss-loop-120b

GPT OSS 120B with the LOOP V2 behavioral prompt layer for structured self‑checking, requirement tracking, and answer refinement. No weight changes or fine‑tuning.

fauxpaslife/gpt-oss-20B-Q5_K_M

12GB Version of GPT-OSS:20B via Unsloth for a slightly smaller footprint with minimal quality loss.