Quantized version of nvidia/Nemotron-Content-Safety-Reasoning-4B
This model was converted to GGUF format from nvidia/Nemotron-Content-Safety-Reasoning-4B using llama.cpp tools. Refer to the original model card for more details on the model.
This model was specially converted for my Harmless Terminal Assistant demo project.
- Downloads last month
- 24
GGUF
Model size
5B params
Architecture
gemma3
Hardware compatibility
Log In to add your hardware
8-bit
Model tree for ARM174G3/Nemotron-Content-Safety-Reasoning-4B-Q8_0-GGUF
Base model
google/gemma-3-4b-pt Finetuned
google/gemma-3-4b-it