Downloads · 30 days
16
4% of all-time downloads
Llama-3.3-8B-Instruct-NVFP4
AlphaOxO/Llama-3.3-8B-Instruct-NVFP4
Llama-3.3-8B-Instruct-NVFP4 is a text generation model from AlphaOxO. Use it when you need the model to write or continue text.
- CPU: AMD Ryzen Threadripper PRO 7995WX - MB: GIGABYTE AI TOP TRX50 - GPU: RTX 50901 - RAM: RDIMM DDR5 5600 128GB2
All-time downloads
396
Public
Parameters
5B
6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6 GB · 100%
Parameter types
How the weights are stored.
U83.5B · 70%
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
Llama 3.3 8B Instruct NVFP4
Using Hardware
- CPU: AMD Ryzen Threadripper PRO 7995WX
- MB: GIGABYTE AI TOP TRX50
- GPU: RTX 5090*1
- RAM: RDIMM DDR5 5600 128GB*2
Using Software
- CUDA version: 13.0
- CUDA driver version: 580.95.05
- pyTorch: 2.10.0+cu130
- transformers: 5.3.0
- llmcompressor: 0.10.0.1
- vllm: 0.17.1
Backbone Model
shb777/Llama-3.3-8B-Instruct-128K
Using Dataset
tatsu-lab/alpaca convert as chat template.
Compare
| -- | origin model(BF16) | Quantization(This Model) |
|---|---|---|
| leaderboard_gpqa | 0.303 | 0.298 |
| VRAM Usage | 14.99 GiB | 5.69 GiB |
- Task
- Text Generation
- Type
- llama
- Created
- Apr 10, 2026
- Updated
- Apr 24, 2026