20+ models
gpt-oss-safeguard-20b and gpt-oss-safeguard-120b are safety reasoning models built-upon gpt-oss
12GB Version of GPT-OSS:20B via Unsloth for a slightly smaller footprint with minimal quality loss.
Abliterated build of OpenAI gpt-oss-20b. Note up front: gpt-oss is highly refusal-robust, so this is a modest reduction, published honestly.
Generic all purpose model. Occasionally may have notable logic, usually Llama-3_3-Nemotron-Super-49B-v1_5 is preferred.
Abstractive summarization using gpt-oss-20B as base model.
Update ollama to 0.11.5+ . Unsloth Dynamic 2.0 Quants achieves superior accuracy & SOTA quantization performance. UD-Q4_K_XL & UD-Q6_K_XL provided.