Gemma-4-12B-it-Uncensored-Heretic-MXFP4-GGUF
MXFP4 GGUF quantization of llmfan46/gemma-4-12B-it-uncensored-heretic - an uncensored/heretic (abliterated) finetune of Google's Gemma 4 12B with vision support.
About MXFP4
MXFP4 (Microscaling FP4) is an open standard (OCP) 4-bit floating point format (E2M1) supported by NVIDIA, AMD, Microsoft, and Meta.
- Works on any GPU with MXFP4 support
- Open standard - not vendor locked
- Block-scaled format with shared scale factors
When to use MXFP4 vs other formats:
- MXFP4 - Open standard, broad hardware support
- NVFP4 - NVIDIA Blackwell native, best performance on RTX 50-series
- Q4_K_M - Best for pre-Blackwell GPUs and CPU inference
Files
| File | Type | Size | Description |
|---|---|---|---|
gemma4-12b-heretic-mxfp4.gguf | MXFP4 | ~6.3 GB | Text model (4.45 BPW) |
mmproj-gemma-4-12b-heretic-f16.gguf | F16 | ~116 MB | Vision encoder (mmproj) |
Quantization Details
| Property | Value |
|---|---|
| Format | MXFP4 (E2M1) |
| Bits Per Weight | 4.45 BPW |
| Source Model | llmfan46/gemma-4-12B-it-uncensored-heretic |
| Architecture | Gemma4UnifiedForConditionalGeneration |
| Layers | 48 |
| Hidden Size | 3840 |
| Context Length | 262144 |
| Vision | Yes (Gemma4V projector) |
| Thinking | Enabled by default (opt-out via enable_thinking=false) |
Model Description
This is an abliterated (uncensored/heretic) finetune of Google's Gemma 4 12B, a multimodal model with both text and vision capabilities. The original model was finetuned to remove safety alignment restrictions while maintaining the model's core capabilities.
Gemma 4 features a hybrid attention architecture with alternating sliding window and full attention layers, native vision encoding, and tool calling support.
Usage
llama.cpp CLI
# Text only
./llama-cli -m gemma4-12b-heretic-mxfp4.gguf -p "Hello" -n 100
# With vision (requires mmproj)
./llama-server -m gemma4-12b-heretic-mxfp4.gguf \
--mmproj mmproj-gemma-4-12b-heretic-f16.gguf \
--host 0.0.0.0 --port 8080 -ngl 99
huggingface-hub
from huggingface_hub import hf_hub_download
model_path = hf_hub_download(
repo_id="FreedomAISVR/Gemma-4-12B-it-Uncensored-Heretic-MXFP4-GGUF",
filename="gemma4-12b-heretic-mxfp4.gguf"
)
mmproj_path = hf_hub_download(
repo_id="FreedomAISVR/Gemma-4-12B-it-Uncensored-Heretic-MXFP4-GGUF",
filename="mmproj-gemma-4-12b-heretic-f16.gguf"
)
Quantization Pipeline
- Download source:
llmfan46/gemma-4-12B-it-uncensored-heretic - Convert to F16 GGUF:
convert_hf_to_gguf.py --outtype f16 - Extract mmproj:
convert_hf_to_gguf.py --mmproj --outtype f16 - Quantize text:
llama-quantize input-f16.gguf output-mxfp4.gguf MXFP4
Hardware Requirements
| Component | Requirement |
|---|---|
| GPU | Any with MXFP4 support, or CPU fallback |
| VRAM | ~7 GB minimum |
| RAM | ~16 GB recommended |
| Storage | ~7 GB |
License
Apache 2.0 (inherited from base model)