Blog

Nemotron-3-Embed-1B compression — experiment archive

Archived July 16, 2026

Supporting data for the blog post The Middle Wasn't Broken This Time. Every method was evaluated on the same two embedding sets — SciFact (1600-doc subset, 300 test queries) and STS-B test (1379 pairs) — encoded with nvidia/Nemotron-3-Embed-1B-BF16. remax and remex rows are means over seeds 0–4. The full harness lives in remax PR #52.

Charts

Numbers (CSV, served raw)

Writeups

Reproducing NVFP4 on a CPU

The reconstruction — FP4 e2m1 weights × FP8 block scales × global scale, dequantized to float32 and run without a GPU — is a single script, bench/nvfp4_dequant_encode.py, with an offline selftest for the FP4 decode. Validated at per-weight cosine 0.9955 vs the BF16 twin.

Files are markdown / CSV / PNG served raw. The narrative reads cleanest in this order: NEMOTRON_MASTER.md → nemotron_master.png → the CSVs.