5 models
gpt-oss-safeguard-20b and gpt-oss-safeguard-120b are safety reasoning models built-upon gpt-oss
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.
Bartowski's GGUF at full BF16 weights. Parameters and Template optimized for tool use.
Generic all purpose model. Occasionally may have notable logic, usually Llama-3_3-Nemotron-Super-49B-v1_5 is preferred.
12GB Version of GPT-OSS:20B via Unsloth for a slightly smaller footprint with minimal quality loss.