RayFernando1337/LLM-Calc
Instantly calculate the maximum size of quantized language models that can fit in your available RAM, helping you optimize your models for inference.
This tool helps you quickly figure out the largest large language model (LLM) that will actually run on your computer's memory. You tell it your available RAM, how much your operating system uses, and the desired quality level of the model, and it tells you the maximum model size (in parameters) you can use. This is for AI developers, researchers, or anyone building or experimenting with LLMs on their own hardware.
253 stars.
Use this if you need to determine the optimal size of a quantized LLM that can fit into your GPU or system RAM for efficient inference or local development.
Not ideal if you are looking for a tool to train LLMs or fine-tune them, or if you are interested in cloud-based LLM deployment where memory management is abstracted away.
Stars
253
Forks
12
Language
TypeScript
License
MIT
Category
Last pushed
Feb 22, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/RayFernando1337/LLM-Calc"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
vllm-project/vllm-ascend
Community maintained hardware plugin for vLLM on Ascend
SemiAnalysisAI/InferenceX
Open Source Continuous Inference Benchmarking Qwen3.5, DeepSeek, GPTOSS - GB200 NVL72 vs MI355X...
kvcache-ai/Mooncake
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
uccl-project/uccl
UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache...
sophgo/tpu-mlir
Machine learning compiler based on MLIR for Sophgo TPU.