# Informal release evaluation: BF16 / INT8 comparison

This community evaluation is provided for reference only and does not represent any official evaluation.

4 paired outputs on NVIDIA GeForce RTX 5090; 2048×2048, 8 steps, offload=model, CFG=1, KV cache enabled.

Warmup excluded. Pixel metrics measure drift, not semantic quality. The suite is small and does not establish a general quality ranking.

| Case | Seed | BF16 s | INT8 s | BF16 peak GiB | INT8 peak GiB | RGB MAE (white) |
|---|---:|---:|---:|---:|---:|---:|
| portrait | 42 | 45.85 | 33.40 | 26.89 | 26.89 | 0.0100 |
| portrait | 123 | 46.31 | 32.99 | 26.89 | 26.89 | 0.0169 |
| edit_boat | 20261009 | 87.84 | 52.01 | 26.93 | 26.93 | 0.0090 |
| edit_boat | 20261010 | 65.72 | 56.79 | 26.93 | 26.93 | 0.0071 |

## Summary

Mean latency: BF16 61.43s; INT8 43.79s.

[Interactive-sized side-by-side gallery](comparison.html). Raw data: comparison.csv, bf16/records.jsonl, int8/records.jsonl. Environment records include package versions and loading overhead.

[Qualitative observations](qualitative.md).

## Interpretation limits

- No CLIP, OCR, human preference, FID or benchmark leaderboard score is claimed.
- Peak CUDA allocated/reserved memory excludes other processes and display usage.
- Measured call latency includes transfers; disk writing and model loading are excluded.
- Paired images may diverge with quantization even when both remain plausible.
- Editing and transparency should be inspected in the gallery, including preserved details.