by Raskoll2 · Agent Tool · ★ 167
LLM Calculator This tool estimates the memory requirements and performance of Hugging Face models based on quantization levels. It fetches model parameters, calculates required memory, and analyzes performance with different RAM/VRAM configurations. Supports Windows, Linux, and macOS, as well as AMD, Intel, and Nvidia GPUs. If you're using an Nvidia GPU, you'll need (which comes with the CUDA toolkit) installed for detection. Warning: This tool is mostly tested on Linux + Nvidia. Results may be inaccurate on other setups.
| Stars | 167 |
| Forks | 13 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 67.55872433423/100 |
| Open Issues | 3 |
| Last Updated | 2025-01-30 |
| Created | 2025-01-27 |
| Platforms | python |
| Est. Tokens | ~10k |
Explore other popular agent tool tools:
LLMcalc is A tool to determine whether or not your PC can run a given LLM. It is categorized as a Agent Tool with 167 GitHub stars.
LLMcalc is primarily written in Python.
You can find installation instructions and usage details in the LLMcalc GitHub repository at github.com/Raskoll2/LLMcalc. The project has 167 stars and 13 forks, indicating an active community.
LLMcalc is released under the MIT license, making it free to use and modify according to the license terms.