CQ3-Qwen3-8B-K4-CodeQuant / codequant_baseline.json
sy128's picture
CodeQuant baseline qwen3_8b K4, single-GPU build
d5b6ff8 verified
Raw
History Blame Contribute Delete
345 Bytes
{
"baseline": "codequant",
"model": "Qwen/Qwen3-8B",
"bits": 2,
"cluster_num": 4,
"calibration_dataset": "mixed",
"max_samples": 512,
"rotation_max_samples": 512,
"sequence_length": 512,
"seconds": 7086.563619456254,
"rotation_seconds": 534.7060408368707,
"cluster_seconds": 6551.857578619383,
"folded_projections": 180
}