Downloads · 30 days
240
5% of all-time downloads
FreedomAISVR/Gemma-4-12B-it-Uncensored-Heretic-NVFP4-GGUF
Gemma-4-12B-it-Uncensored-Heretic-NVFP4-GGUF is a image-text-to-text model from FreedomAISVR. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for gguf. The card lists the license as apache-2.0.
NVFP4 GGUF quantization of llmfan46/gemma-4-12B-it-uncensored-heretic - an uncensored/heretic (abliterated) finetune of Google's Gemma 4 12B with vision support.
Downloads · 30 days
240
5% of all-time downloads
All-time downloads
4.8K
Public
Repo size
7.1 GB
Likes
4
Public
Click a slice to open those files.
.gguf7.1 GB · 100%
From the Hugging Face model README
NVFP4 GGUF quantization of llmfan46/gemma-4-12B-it-uncensored-heretic - an uncensored/heretic (abliterated) finetune of Google's Gemma 4 12B with vision support.
NVFP4 is NVIDIA's native 4-bit floating point format (E4M3) designed for Blackwell architecture GPUs (RTX 50-series, B100/B200). It provides:
When to use NVFP4 vs other formats:
| File | Type | Size | Description |
|---|---|---|---|
gemma4-12b-heretic-nvfp4.gguf | NVFP4 | ~6.5 GB | Text model (4.68 BPW) |
mmproj-gemma-4-12b-heretic-f16.gguf | F16 | ~116 MB | Vision encoder (mmproj) |
| Property | Value |
|---|---|
| Format | NVFP4 (E4M3) |
| Bits Per Weight | 4.68 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) |
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.
# Text only
./llama-cli -m gemma4-12b-heretic-nvfp4.gguf -p "Hello" -n 100
# With vision (requires mmproj)
./llama-server -m gemma4-12b-heretic-nvfp4.gguf \
--mmproj mmproj-gemma-4-12b-heretic-f16.gguf \
--host 0.0.0.0 --port 8080 -ngl 99
gemma4-12b-heretic-nvfp4.gguf as the modelmmproj-gemma-4-12b-heretic-f16.gguf as the mmprojfrom huggingface_hub import hf_hub_download
model_path = hf_hub_download(
repo_id="FreedomAISVR/Gemma-4-12B-it-Uncensored-Heretic-NVFP4-GGUF",
filename="gemma4-12b-heretic-nvfp4.gguf"
)
mmproj_path = hf_hub_download(
repo_id="FreedomAISVR/Gemma-4-12B-it-Uncensored-Heretic-NVFP4-GGUF",
filename="mmproj-gemma-4-12b-heretic-f16.gguf"
)
llmfan46/gemma-4-12B-it-uncensored-hereticconvert_hf_to_gguf.py --outtype f16convert_hf_to_gguf.py --mmproj --outtype f16llama-quantize input-f16.gguf output-nvfp4.gguf NVFP4| Component | Requirement |
|---|---|
| GPU | NVIDIA Blackwell (RTX 50-series) for full acceleration |
| VRAM | ~7 GB minimum |
| RAM | ~16 GB recommended |
| Storage | ~7 GB |
Apache 2.0 (inherited from base model)