KV-Cache Receipts — nine ≈128K users on one A100 (vLLM) Collection Three-arm, needle-gated serving receipts (fp16 / fp8-KV / compressed) — reproducible for ≈$12 with one command. • 5 items • Updated Aug 25
Hi-Fi Quants — calibrated GGUFs with KLD receipts Collection Calibration-aware Q4-class GGUFs at identical size to leading community quants, with measured KLD receipts. • 8 items • Updated Aug 24 • 1
Hi-Fi Quants — calibrated GGUFs with KLD receipts Collection Calibration-aware Q4-class GGUFs at identical size to leading community quants, with measured KLD receipts. • 8 items • Updated Aug 24 • 1