RahulSChand/gpu_poor

Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization

15 best points · 4 comments · 1 Hacker News post · 1,402 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: Can your GPU run this LLM? (15 points, 4 comments, by ALTRC0320, 2023-09-29)