Downloads · 30 days
24
12% of all-time downloads
Llama-Guard-4-12B-NVFP4
tengsnake/Llama-Guard-4-12B-NVFP4
Llama-Guard-4-12B-NVFP4 is a text generation model from tengsnake. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as llama4.
Quantized version of: meta-llama/Llama-Guard-4-12B
All-time downloads
207
Public
Parameters
12B
9.5 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.safetensors9.5 GB · 100%
Parameter types
How the weights are stored.
U810.1B · 84%
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
Quantized version of: meta-llama/Llama-Guard-4-12B
Quantization Details
- Language Model Body (Text Body): All Self-Attention (
q_proj,k_proj,v_proj,o_proj) and MLP (gate_proj,up_proj,down_proj) layers are successfully compressed to NVFP4. - Unquantized (Retained in BF16):
lm_head(retained in BF16 to resolve vLLM loading compatibility issues)embed_tokens(token embedding layer)vision_model&multi_modal_projector(vision-related components)
- Task
- Text Generation
- Library
- transformers
- Type
- llama4
- License
- llama4
- Languages
- en
- Created
- Jul 28, 2026
- Updated
- Jul 29, 2026