NVIDIA-SMI
Read the Portuguese translation →
Mentioned in
Section titled “Mentioned in”- Amos 1 Small: 69.5% Accurate, Zero Tokens, 5 GB VRAM
- 70B on a 4GB GPU? I Tested It (2 Minutes Per Token)
Related
Section titled “Related”RunPod, Python, UV, Apache License 2.0, RTX 4060, PyTorch, quantização de 4 bits, llama.cpp