0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-GGUF

Granite 4.2 3B — Heretic NX PRIME (GGUF)

GGUF release of a capability-preserving residual-stream edit of ibm-granite/granite-4.2-3b. This is the beta 2.4, rank-16 protected candidate selected on a fixed refusal/KL frontier and validated independently after materialization.

This is a static weight edit, not a LoRA and not a fine-tune. No adapter or custom runtime hook is required.

Files

All three files contain the Granite tokenizer and chat template and were smoke-tested with llama.cpp b10621.

Evaluation

The paired capability slice contains ARC-Challenge, HellaSwag and MMLU. Its bootstrap mean difference is +0.94 percentage point, with a 95% interval of [-0.35, +2.22] points.

KL depends on the exact runtime being measured:

The second value includes independent NF4 quantization noise and should not be presented as a pure BF16-to-BF16 KL measurement. The GGUF quantizations were load-tested, but their full 104-row behavioral scores are not claimed to be identical to the BF16 checkpoint.

The 104-row refusal result is a lexical explicit-refusal proxy. It is not a measure of semantic task success and is not a universal model-quality score. See `EVALUATION_SUMMARY.md` and the included JSON reports for the exact protocols.

What was edited

• —Source revision: b7e947307dd2efb3ad3b853b0e8a7e75f8ad4ac2
• —Protected residual-stream axis rank: 16
• —Strength: beta = 2.4
• —Edited layers: 25–36
• —Edited projections: attention output and MLP down projections
• —Materialization: norm-preserving static weight edits in BF16
• —Edited tensors: 24

LM Studio

Download one GGUF file and place it in your LM Studio models directory. Q80 is the default recommendation; Q4K_M is appropriate when RAM/VRAM is tight.

hf download 0xzknw/Granite-4.2-3B-Heretic-NX-PRIME-GGUF Granite-4.2-3B-Heretic-NX-PRIME-Q8_0.gguf --local-dir "$env:USERPROFILE\.lmstudio\models\0xzknw\Granite-4.2-3B-Heretic-NX-PRIME-GGUF"

If LM Studio is already open, refresh the model list or restart the app after the download completes.

llama.cpp

llama-cli -m Granite-4.2-3B-Heretic-NX-PRIME-Q8_0.gguf -cnv

Granite 4.2 supports thinking mode through its embedded chat template.

Reproducibility

SHA-256 checksums:

0edede4dd173c778e4a47969188d54753bf8edb3dd62e097f9b985af9ffcf36d  Granite-4.2-3B-Heretic-NX-PRIME-BF16.gguf
9135527c35629202e63938ebe11d039071c45f91326d031fcad44d0ffd4033f0  Granite-4.2-3B-Heretic-NX-PRIME-Q8_0.gguf
56c040b4c55a31b542fe8beb8b712f3b6ee5531018116ea74af0b0573cb9058d  Granite-4.2-3B-Heretic-NX-PRIME-Q4_K_M.gguf

The editing engine and reproducibility code are available in Heretic NX.

License and use

The source model is Apache-2.0 and this release preserves that license. Model editing reduces learned refusal behavior; users remain responsible for how they deploy and use the model.