# Weight Quantization Footprints > Source-anchored research for Weight Quantization Footprints. Run status: COMPLETED. Parent: [16 GB VRAM residency budgeting](https://llms-explorer.com/tree/16-gb-vram-residency-budgeting/) · 1 facets · 2 facts · page: https://llms-explorer.com/tree/weight-quantization-footprints/ ## Measurements and reference values - A 14-billion parameter model: FP16 - 28.0 GB, FP8/INT8 - 14.0 GB, 4-bit (Q4_K_M) - 7.62 GB (high confidence) — [source](https://github.com/ggerganov/llama.cpp) - On 16 GB RTX 5080: Q4_K_M leaves 8.38 GB for KV cache and scratch (high confidence) — [source](https://github.com/ggerganov/llama.cpp)