{ "experiment": "WO-BNB-BASELINE-01", "model": "Zamba2-7B-Instruct", "eval_params": { "dataset": "wikitext/wikitext-2-raw-v1/test", "max_length": 2048, "stride": 512, "speed_iters": 100, "speed_seq_len": 512 }, "configs": { "dense_bf16": { "name": "Dense BF16", "ppl": 3.7216, "n_tokens": 334660, "n_chunks": 651, "vram_load_mb": 14032.0, "vram_peak_eval_mb": 16173.8, "vram_peak_speed_mb": 14396.5, "tokens_per_sec": 4385.2, "speed_test_elapsed_s": 11.68, "config_elapsed_s": 297.3 }, "bnb_8bit": { "name": "bnb 8-bit (LLM.int8)", "ppl": 3.7335, "n_tokens": 334660, "n_chunks": 651, "vram_load_mb": 7831.3, "vram_peak_eval_mb": 10011.6, "vram_peak_speed_mb": 8188.0, "tokens_per_sec": 2165.3, "speed_test_elapsed_s": 23.65, "config_elapsed_s": 334.3 }, "bnb_4bit_nf4": { "name": "bnb 4-bit NF4", "ppl": 3.8916, "n_tokens": 334660, "n_chunks": 651, "vram_load_mb": 5106.6, "vram_peak_eval_mb": 7240.4, "vram_peak_speed_mb": 5590.6, "tokens_per_sec": 3468.4, "speed_test_elapsed_s": 14.76, "config_elapsed_s": 332.6 }, "hxq_2dvq_k4096": { "name": "HXQ 2D VQ k=4096", "ppl": 3.8454, "n_tokens": 334660, "n_chunks": 651, "vram_load_mb": 14040.1, "vram_peak_eval_mb": 16173.8, "vram_peak_speed_mb": 14396.5, "tokens_per_sec": 4384.5, "speed_test_elapsed_s": 11.68, "config_elapsed_s": 343.0 } }, "cost": { "wall_time_s": 1311.822, "cpu_time_s": 1440.214, "peak_memory_mb": 16490.8, "python_version": "3.10.12", "hostname": "74efa4ce-5ef6-427c-b27b-336ce89875b5", "timestamp_start": "2026-04-01T21:29:26", "timestamp_end": "2026-04-01T21:51:18", "gpu": "NVIDIA GeForce RTX 4090" } }