AI & Local
LLM Memory Calculator
Enter a model's parameters, weight precision, context length and KV-cache precision to estimate weight memory, KV-cache size and total memory — so you know whether it will fit before you download it.
Free · runs in your browser · no sign-up to use.
Assumes 0.5 bytes/param for weights and a 2-byte KV cache, plus ~18% runtime overhead. KV is estimated from the parameter count.
Estimated memory
Weights3.73 GB
KV cache2.00 GB
Runtime overhead1.03 GB
Total6.76 GB
Estimate, not a guarantee. Actual use varies with the runtime, batching, and quant format.