npario / Model details
gemma-4-31B-it-qat-uncensored-heretic-UDmerge-GGUF
npario/gemma-4-31B-it-qat-uncensored-heretic-UDmerge-GGUF
About this model
npario's merged Gemma-4-31B derivative, released as GGUF weights under Apache-2.0. The creator says it grafts abliterated tensors from llmfan46's uncensored QAT BF16 checkpoint onto Unsloth's lossless Q4_0 quant, producing two variants: UDmerge-Q4_K_XL (abliterated layers quantized to Q4_0) and UDmerge-Q4_K_XXL (abliterated layers quantized to Q8_0). According to the model card, the XXL variant aims to improve refusal rates while maintaining speed. The creator's tests show refusal rates of 34% for XL and 20% for XXL on their adapted harmful-behaviors dataset. No independent verification of these claims is provided here.
Description sources
Source-based description, not an independent evaluation. Check the linked sources for the creator’s claims and limitations.
Size and formats
- Base model
- llmfan46/gemma-4-31B-it-qat-q4_0-unquantized-uncensored-heretic, unsloth/gemma-4-31B-it-qat-GGUF
- Parameters
- Unknown
- Main repository formats
- GGUF
- License tag
- apache-2.0
- Languages
- Unknown
- Last updated
- 2026-10-23 · 02:47:17.000 UTC
What changed
Model types are creator-reported, not independently tested. These labels describe source metadata, not a guarantee of behavior.
- abliteratedsource tag:
abliterated
- uncensoredsource tag:
base_model:llmfan46/gemma-4-31B-it-qat-q4_0-unquantized-uncensored-heretic
- uncensoredsource tag:
base_model:merge:llmfan46/gemma-4-31B-it-qat-q4_0-unquantized-uncensored-heretic
- uncensoredsource tag:
uncensored
- uncensoredmodel name:
gemma-4-31B-it-qat-uncensored-heretic-UDmerge-GGUF
- mergedsource tag:
base_model:merge:llmfan46/gemma-4-31B-it-qat-q4_0-unquantized-uncensored-heretic
- mergedsource tag:
base_model:merge:unsloth/gemma-4-31B-it-qat-GGUF
Family evidence
These groupings are source-reported. Explicit base identifiers take priority over generic architecture tags.
- Gemma: Base model: llmfan46/gemma-4-31B-it-qat-q4_0-unquantized-uncensored-heretic
- Gemma: Base model: unsloth/gemma-4-31B-it-qat-GGUF
Available versions
Only explicitly linked variants are grouped here. Check the original repository for available files.
- Main repository files ↗GGUF
- No other explicitly linked versions recorded.
Customize or build on this model
Listed from public GitHub data, not tested by us. Read the code and license before you run anything.
Tools to customize it further
Make a smaller download (quantize)
- llama.cpp ↗ ★ 132,124
Runs models locally and includes the tools behind most GGUF files. A conversion script turns Hugging Face weights into GGUF, and llama-quantize shrinks a high-precision GGUF to lower-bit formats, which can cost some accuracy.
Learn the techniques
- LLM Course ↗ ★ 84,633
A free course with roadmaps and Colab notebooks. Its notebooks include one-click tools for merging with MergeKit, quantizing to GGUF, GPTQ, EXL2, AWQ and HQQ, and automatic abliteration with custom datasets.
Source provenance
- Downloads
- 51
- Likes
- 1
- Metadata checked
- 2026-10-23 · 23:39:28 UTC
- First seen in index
- 2026-10-23 · 23:39:28 UTC
- Source revision
- 113a192e28f8e88401d65341eef4d5d01d34ed19
Source-card excerpt
Source model card excerpt: UPDATE 2026-07-20: Download & use Google's new chat template from here for better speed and accurancy. See Unsloth's post for details. --- WARNING: Created
From npario/gemma-4-31B-it-qat-uncensored-heretic-UDmerge-GGUF. Creator model-card excerpt, not an independent review.
Inspect before you run
Low refusal is not proof of correctness. Outputs can be inaccurate, harmful, or biased. Review the model card, license and files yourself. A license tag is not commercial-use advice. Parameter counts are source metadata; no hardware compatibility is implied.
This directory does not run, host, redistribute, or test model weights.
Collection rules & limitations ↗