Context-optimized variant of IBM's Granite 4.2 3B model, tuned for lightweight tool-use on GPU-constrained hosts.
Reduced-refusal IBM Granite 4.2 3B via Heretic: 27/100 refusals (from 98), KL 0.085. Apache-2.0, multilingual.
granite4.2:30b-256k-bf16
UNCENSORED (Abliterated + SecOps LoRA) — IBM Granite 4.2 Uncensored (8B Compact & 30B Flagship 128K Editions: :8b, :30b-q3, :30b, :30b-q6, :30b-q8) — Trained & Orthogonally Abliterated by Erik Tonon.
pulled as BF16, requant to IQ4_NL, with combined_en_huge as dataset (English + Coding focus)
pulled as BF16, vocab slice (combined_en_huge) requant to IQ4_NL (combined_en_huge) -- (English + Coding focus) - ~20% faster than Q4_K_M