{ "artifact_format": "orbitquant-multicomponent-v1", "source_model_id": "MiniMaxAI/MiniMax-H3", "source_revision": "73372e6cf53e414edd3ab03e357717fb0602e758", "source_license": "minimax-h3-community-license-agreement", "repo_id": "WaveCut/MiniMax-H3-OrbitQuant-W4A4", "visibility": "public", "quant_method": "orbitquant", "recipe": "native-w4a4-text-and-denoisers-source-fp32-vaes", "weight_bits": 4, "activation_bits": 4, "w4a4_components": [ "transformer", "transformer_ref", "text_encoder" ], "source_precision_components": [ "vae", "audio_vae" ], "calibration_data": null, "orbitquant_version": "0.9.2", "orbitquant_revision": "cd58b4ecf77f22b8c4116b3d0b7d4af258e16ba3", "diffusers_revision": "abc5e9bf71fd38f53cd471bc3acaa84bc5ecbfdc", "components": [ { "status": "complete", "component": "transformer", "framework": "diffusers", "class_name": "MiniMaxH3Transformer3DModel", "component_mode": "w4a4", "source_weight_bytes": 66280430080, "artifact_bytes": 18283368121, "load_and_quantize_seconds": 805.4532320899889, "save_seconds": 121.72156953113154, "wall_seconds": 927.2030724789947, "rss_before_bytes": 810000384, "rss_after_bytes": 19391897600, "released_source_tensor_bytes": 64546406400, "source_page_release_failures": 0, "gpu": { "device": "NVIDIA RTX PRO 6000 Blackwell Server Edition", "capability": [ 12, 0 ], "free_bytes": 101292179456, "total_bytes": 101973950464, "allocated_bytes": 136192, "reserved_bytes": 2097152, "peak_allocated_bytes": 25827328, "peak_reserved_bytes": 46137344 }, "orbitquant_module_count": 300, "adaln_int4_module_count": 50, "bf16_linear_module_count": 20, "orbitquant_modules": [ "transformer_blocks.0.attn.to_q", "transformer_blocks.0.attn.to_k", "transformer_blocks.0.attn.to_v", "transformer_blocks.0.attn.to_out.0", "transformer_blocks.0.ff.net.0.proj", "transformer_blocks.0.ff.net.2", "transformer_blocks.1.attn.to_q", "transformer_blocks.1.attn.to_k", "transformer_blocks.1.attn.to_v", "transformer_blocks.1.attn.to_out.0", "transformer_blocks.1.ff.net.0.proj", "transformer_blocks.1.ff.net.2", "transformer_blocks.2.attn.to_q", "transformer_blocks.2.attn.to_k", "transformer_blocks.2.attn.to_v", "transformer_blocks.2.attn.to_out.0", "transformer_blocks.2.ff.net.0.proj", "transformer_blocks.2.ff.net.2", "transformer_blocks.3.attn.to_q", "transformer_blocks.3.attn.to_k", "transformer_blocks.3.attn.to_v", "transformer_blocks.3.attn.to_out.0", "transformer_blocks.3.ff.net.0.proj", "transformer_blocks.3.ff.net.2", "transformer_blocks.4.attn.to_q", "transformer_blocks.4.attn.to_k", "transformer_blocks.4.attn.to_v", "transformer_blocks.4.attn.to_out.0", "transformer_blocks.4.ff.net.0.proj", "transformer_blocks.4.ff.net.2", "transformer_blocks.5.attn.to_q", "transformer_blocks.5.attn.to_k", "transformer_blocks.5.attn.to_v", "transformer_blocks.5.attn.to_out.0", "transformer_blocks.5.ff.net.0.proj", "transformer_blocks.5.ff.net.2", "transformer_blocks.6.attn.to_q", "transformer_blocks.6.attn.to_k", "transformer_blocks.6.attn.to_v", "transformer_blocks.6.attn.to_out.0", "transformer_blocks.6.ff.net.0.proj", "transformer_blocks.6.ff.net.2", "transformer_blocks.7.attn.to_q", "transformer_blocks.7.attn.to_k", "transformer_blocks.7.attn.to_v", "transformer_blocks.7.attn.to_out.0", "transformer_blocks.7.ff.net.0.proj", "transformer_blocks.7.ff.net.2", "transformer_blocks.8.attn.to_q", "transformer_blocks.8.attn.to_k", "transformer_blocks.8.attn.to_v", "transformer_blocks.8.attn.to_out.0", "transformer_blocks.8.ff.net.0.proj", "transformer_blocks.8.ff.net.2", "transformer_blocks.9.attn.to_q", "transformer_blocks.9.attn.to_k", "transformer_blocks.9.attn.to_v", "transformer_blocks.9.attn.to_out.0", "transformer_blocks.9.ff.net.0.proj", "transformer_blocks.9.ff.net.2", "transformer_blocks.10.attn.to_q", "transformer_blocks.10.attn.to_k", "transformer_blocks.10.attn.to_v", "transformer_blocks.10.attn.to_out.0", "transformer_blocks.10.ff.net.0.proj", "transformer_blocks.10.ff.net.2", "transformer_blocks.11.attn.to_q", "transformer_blocks.11.attn.to_k", "transformer_blocks.11.attn.to_v", "transformer_blocks.11.attn.to_out.0", "transformer_blocks.11.ff.net.0.proj", "transformer_blocks.11.ff.net.2", "transformer_blocks.12.attn.to_q", "transformer_blocks.12.attn.to_k", "transformer_blocks.12.attn.to_v", "transformer_blocks.12.attn.to_out.0", "transformer_blocks.12.ff.net.0.proj", "transformer_blocks.12.ff.net.2", "transformer_blocks.13.attn.to_q", "transformer_blocks.13.attn.to_k", "transformer_blocks.13.attn.to_v", "transformer_blocks.13.attn.to_out.0", "transformer_blocks.13.ff.net.0.proj", "transformer_blocks.13.ff.net.2", "transformer_blocks.14.attn.to_q", "transformer_blocks.14.attn.to_k", "transformer_blocks.14.attn.to_v", "transformer_blocks.14.attn.to_out.0", "transformer_blocks.14.ff.net.0.proj", "transformer_blocks.14.ff.net.2", "transformer_blocks.15.attn.to_q", "transformer_blocks.15.attn.to_k", "transformer_blocks.15.attn.to_v", "transformer_blocks.15.attn.to_out.0", "transformer_blocks.15.ff.net.0.proj", "transformer_blocks.15.ff.net.2", "transformer_blocks.16.attn.to_q", "transformer_blocks.16.attn.to_k", "transformer_blocks.16.attn.to_v", "transformer_blocks.16.attn.to_out.0", "transformer_blocks.16.ff.net.0.proj", "transformer_blocks.16.ff.net.2", "transformer_blocks.17.attn.to_q", "transformer_blocks.17.attn.to_k", "transformer_blocks.17.attn.to_v", "transformer_blocks.17.attn.to_out.0", "transformer_blocks.17.ff.net.0.proj", "transformer_blocks.17.ff.net.2", "transformer_blocks.18.attn.to_q", "transformer_blocks.18.attn.to_k", "transformer_blocks.18.attn.to_v", "transformer_blocks.18.attn.to_out.0", "transformer_blocks.18.ff.net.0.proj", "transformer_blocks.18.ff.net.2", "transformer_blocks.19.attn.to_q", "transformer_blocks.19.attn.to_k", "transformer_blocks.19.attn.to_v", "transformer_blocks.19.attn.to_out.0", "transformer_blocks.19.ff.net.0.proj", "transformer_blocks.19.ff.net.2", "transformer_blocks.20.attn.to_q", "transformer_blocks.20.attn.to_k", "transformer_blocks.20.attn.to_v", "transformer_blocks.20.attn.to_out.0", "transformer_blocks.20.ff.net.0.proj", "transformer_blocks.20.ff.net.2", "transformer_blocks.21.attn.to_q", "transformer_blocks.21.attn.to_k", "transformer_blocks.21.attn.to_v", "transformer_blocks.21.attn.to_out.0", "transformer_blocks.21.ff.net.0.proj", "transformer_blocks.21.ff.net.2", "transformer_blocks.22.attn.to_q", "transformer_blocks.22.attn.to_k", "transformer_blocks.22.attn.to_v", "transformer_blocks.22.attn.to_out.0", "transformer_blocks.22.ff.net.0.proj", "transformer_blocks.22.ff.net.2", "transformer_blocks.23.attn.to_q", "transformer_blocks.23.attn.to_k", "transformer_blocks.23.attn.to_v", "transformer_blocks.23.attn.to_out.0", "transformer_blocks.23.ff.net.0.proj", "transformer_blocks.23.ff.net.2", "transformer_blocks.24.attn.to_q", "transformer_blocks.24.attn.to_k", "transformer_blocks.24.attn.to_v", "transformer_blocks.24.attn.to_out.0", "transformer_blocks.24.ff.net.0.proj", "transformer_blocks.24.ff.net.2", "transformer_blocks.25.attn.to_q", "transformer_blocks.25.attn.to_k", "transformer_blocks.25.attn.to_v", "transformer_blocks.25.attn.to_out.0", "transformer_blocks.25.ff.net.0.proj", "transformer_blocks.25.ff.net.2", "transformer_blocks.26.attn.to_q", "transformer_blocks.26.attn.to_k", "transformer_blocks.26.attn.to_v", "transformer_blocks.26.attn.to_out.0", "transformer_blocks.26.ff.net.0.proj", "transformer_blocks.26.ff.net.2", "transformer_blocks.27.attn.to_q", "transformer_blocks.27.attn.to_k", "transformer_blocks.27.attn.to_v", "transformer_blocks.27.attn.to_out.0", "transformer_blocks.27.ff.net.0.proj", "transformer_blocks.27.ff.net.2", "transformer_blocks.28.attn.to_q", "transformer_blocks.28.attn.to_k", "transformer_blocks.28.attn.to_v", "transformer_blocks.28.attn.to_out.0", "transformer_blocks.28.ff.net.0.proj", "transformer_blocks.28.ff.net.2", "transformer_blocks.29.attn.to_q", "transformer_blocks.29.attn.to_k", "transformer_blocks.29.attn.to_v", "transformer_blocks.29.attn.to_out.0", "transformer_blocks.29.ff.net.0.proj", "transformer_blocks.29.ff.net.2", "transformer_blocks.30.attn.to_q", "transformer_blocks.30.attn.to_k", "transformer_blocks.30.attn.to_v", "transformer_blocks.30.attn.to_out.0", "transformer_blocks.30.ff.net.0.proj", "transformer_blocks.30.ff.net.2", "transformer_blocks.31.attn.to_q", "transformer_blocks.31.attn.to_k", "transformer_blocks.31.attn.to_v", "transformer_blocks.31.attn.to_out.0", "transformer_blocks.31.ff.net.0.proj", "transformer_blocks.31.ff.net.2", "transformer_blocks.32.attn.to_q", "transformer_blocks.32.attn.to_k", "transformer_blocks.32.attn.to_v", "transformer_blocks.32.attn.to_out.0", "transformer_blocks.32.ff.net.0.proj", "transformer_blocks.32.ff.net.2", "transformer_blocks.33.attn.to_q", "transformer_blocks.33.attn.to_k", "transformer_blocks.33.attn.to_v", "transformer_blocks.33.attn.to_out.0", "transformer_blocks.33.ff.net.0.proj", "transformer_blocks.33.ff.net.2", "transformer_blocks.34.attn.to_q", "transformer_blocks.34.attn.to_k", "transformer_blocks.34.attn.to_v", "transformer_blocks.34.attn.to_out.0", "transformer_blocks.34.ff.net.0.proj", "transformer_blocks.34.ff.net.2", "transformer_blocks.35.attn.to_q", "transformer_blocks.35.attn.to_k", "transformer_blocks.35.attn.to_v", "transformer_blocks.35.attn.to_out.0", "transformer_blocks.35.ff.net.0.proj", "transformer_blocks.35.ff.net.2", "transformer_blocks.36.attn.to_q", "transformer_blocks.36.attn.to_k", "transformer_blocks.36.attn.to_v", "transformer_blocks.36.attn.to_out.0", "transformer_blocks.36.ff.net.0.proj", "transformer_blocks.36.ff.net.2", "transformer_blocks.37.attn.to_q", "transformer_blocks.37.attn.to_k", "transformer_blocks.37.attn.to_v", "transformer_blocks.37.attn.to_out.0", "transformer_blocks.37.ff.net.0.proj", "transformer_blocks.37.ff.net.2", "transformer_blocks.38.attn.to_q", "transformer_blocks.38.attn.to_k", "transformer_blocks.38.attn.to_v", "transformer_blocks.38.attn.to_out.0", "transformer_blocks.38.ff.net.0.proj", "transformer_blocks.38.ff.net.2", "transformer_blocks.39.attn.to_q", "transformer_blocks.39.attn.to_k", "transformer_blocks.39.attn.to_v", "transformer_blocks.39.attn.to_out.0", "transformer_blocks.39.ff.net.0.proj", "transformer_blocks.39.ff.net.2", "transformer_blocks.40.attn.to_q", "transformer_blocks.40.attn.to_k", "transformer_blocks.40.attn.to_v", "transformer_blocks.40.attn.to_out.0", "transformer_blocks.40.ff.net.0.proj", "transformer_blocks.40.ff.net.2", "transformer_blocks.41.attn.to_q", "transformer_blocks.41.attn.to_k", "transformer_blocks.41.attn.to_v", "transformer_blocks.41.attn.to_out.0", "transformer_blocks.41.ff.net.0.proj", "transformer_blocks.41.ff.net.2", "transformer_blocks.42.attn.to_q", "transformer_blocks.42.attn.to_k", "transformer_blocks.42.attn.to_v", "transformer_blocks.42.attn.to_out.0", "transformer_blocks.42.ff.net.0.proj", "transformer_blocks.42.ff.net.2", "transformer_blocks.43.attn.to_q", "transformer_blocks.43.attn.to_k", "transformer_blocks.43.attn.to_v", "transformer_blocks.43.attn.to_out.0", "transformer_blocks.43.ff.net.0.proj", "transformer_blocks.43.ff.net.2", "transformer_blocks.44.attn.to_q", "transformer_blocks.44.attn.to_k", "transformer_blocks.44.attn.to_v", "transformer_blocks.44.attn.to_out.0", "transformer_blocks.44.ff.net.0.proj", "transformer_blocks.44.ff.net.2", "transformer_blocks.45.attn.to_q", "transformer_blocks.45.attn.to_k", "transformer_blocks.45.attn.to_v", "transformer_blocks.45.attn.to_out.0", "transformer_blocks.45.ff.net.0.proj", "transformer_blocks.45.ff.net.2", "transformer_blocks.46.attn.to_q", "transformer_blocks.46.attn.to_k", "transformer_blocks.46.attn.to_v", "transformer_blocks.46.attn.to_out.0", "transformer_blocks.46.ff.net.0.proj", "transformer_blocks.46.ff.net.2", "transformer_blocks.47.attn.to_q", "transformer_blocks.47.attn.to_k", "transformer_blocks.47.attn.to_v", "transformer_blocks.47.attn.to_out.0", "transformer_blocks.47.ff.net.0.proj", "transformer_blocks.47.ff.net.2", "transformer_blocks.48.attn.to_q", "transformer_blocks.48.attn.to_k", "transformer_blocks.48.attn.to_v", "transformer_blocks.48.attn.to_out.0", "transformer_blocks.48.ff.net.0.proj", "transformer_blocks.48.ff.net.2", "transformer_blocks.49.attn.to_q", "transformer_blocks.49.attn.to_k", "transformer_blocks.49.attn.to_v", "transformer_blocks.49.attn.to_out.0", "transformer_blocks.49.ff.net.0.proj", "transformer_blocks.49.ff.net.2" ], "adaln_int4_modules": [ "transformer_blocks.0.adaln_proj.linear", "transformer_blocks.1.adaln_proj.linear", "transformer_blocks.2.adaln_proj.linear", "transformer_blocks.3.adaln_proj.linear", "transformer_blocks.4.adaln_proj.linear", "transformer_blocks.5.adaln_proj.linear", "transformer_blocks.6.adaln_proj.linear", "transformer_blocks.7.adaln_proj.linear", "transformer_blocks.8.adaln_proj.linear", "transformer_blocks.9.adaln_proj.linear", "transformer_blocks.10.adaln_proj.linear", "transformer_blocks.11.adaln_proj.linear", "transformer_blocks.12.adaln_proj.linear", "transformer_blocks.13.adaln_proj.linear", "transformer_blocks.14.adaln_proj.linear", "transformer_blocks.15.adaln_proj.linear", "transformer_blocks.16.adaln_proj.linear", "transformer_blocks.17.adaln_proj.linear", "transformer_blocks.18.adaln_proj.linear", "transformer_blocks.19.adaln_proj.linear", "transformer_blocks.20.adaln_proj.linear", "transformer_blocks.21.adaln_proj.linear", "transformer_blocks.22.adaln_proj.linear", "transformer_blocks.23.adaln_proj.linear", "transformer_blocks.24.adaln_proj.linear", "transformer_blocks.25.adaln_proj.linear", "transformer_blocks.26.adaln_proj.linear", "transformer_blocks.27.adaln_proj.linear", "transformer_blocks.28.adaln_proj.linear", "transformer_blocks.29.adaln_proj.linear", "transformer_blocks.30.adaln_proj.linear", "transformer_blocks.31.adaln_proj.linear", "transformer_blocks.32.adaln_proj.linear", "transformer_blocks.33.adaln_proj.linear", "transformer_blocks.34.adaln_proj.linear", "transformer_blocks.35.adaln_proj.linear", "transformer_blocks.36.adaln_proj.linear", "transformer_blocks.37.adaln_proj.linear", "transformer_blocks.38.adaln_proj.linear", "transformer_blocks.39.adaln_proj.linear", "transformer_blocks.40.adaln_proj.linear", "transformer_blocks.41.adaln_proj.linear", "transformer_blocks.42.adaln_proj.linear", "transformer_blocks.43.adaln_proj.linear", "transformer_blocks.44.adaln_proj.linear", "transformer_blocks.45.adaln_proj.linear", "transformer_blocks.46.adaln_proj.linear", "transformer_blocks.47.adaln_proj.linear", "transformer_blocks.48.adaln_proj.linear", "transformer_blocks.49.adaln_proj.linear" ], "bf16_linear_modules": [ "proj_in", "audio_proj_in", "context_embedder", "time_embedder.linear_1", "time_embedder.linear_2", "token_refiner.refiner_blocks.0.attn.to_q", "token_refiner.refiner_blocks.0.attn.to_k", "token_refiner.refiner_blocks.0.attn.to_v", "token_refiner.refiner_blocks.0.attn.to_out.0", "token_refiner.refiner_blocks.0.ff.net.0.proj", "token_refiner.refiner_blocks.0.ff.net.2", "token_refiner.refiner_blocks.1.attn.to_q", "token_refiner.refiner_blocks.1.attn.to_k", "token_refiner.refiner_blocks.1.attn.to_v", "token_refiner.refiner_blocks.1.attn.to_out.0", "token_refiner.refiner_blocks.1.ff.net.0.proj", "token_refiner.refiner_blocks.1.ff.net.2", "norm_out.linear", "proj_out", "audio_proj_out" ], "quantized_linear_weight_parameters": 32273203200, "skipped_linear_weight_parameters": 844333056, "linear_weight_parameters": 33117536256, "linear_parameter_coverage": 0.9745049556382073, "packed_module_state_bytes": 16558796800, "full_dequantized_cache_count": 0 }, { "status": "complete", "component": "transformer_ref", "framework": "diffusers", "class_name": "MiniMaxH3Transformer3DModel", "component_mode": "w4a4", "source_weight_bytes": 66280430080, "artifact_bytes": 18283368121, "load_and_quantize_seconds": 1078.1752384407446, "save_seconds": 527.8808484538458, "wall_seconds": 1606.061271655839, "rss_before_bytes": 810053632, "rss_after_bytes": 21555634176, "released_source_tensor_bytes": 64546406400, "source_page_release_failures": 0, "gpu": { "device": "NVIDIA RTX PRO 6000 Blackwell Server Edition", "capability": [ 12, 0 ], "free_bytes": 101292179456, "total_bytes": 101973950464, "allocated_bytes": 136192, "reserved_bytes": 2097152, "peak_allocated_bytes": 25827328, "peak_reserved_bytes": 46137344 }, "orbitquant_module_count": 300, "adaln_int4_module_count": 50, "bf16_linear_module_count": 20, "orbitquant_modules": [ "transformer_blocks.0.attn.to_q", "transformer_blocks.0.attn.to_k", "transformer_blocks.0.attn.to_v", "transformer_blocks.0.attn.to_out.0", "transformer_blocks.0.ff.net.0.proj", "transformer_blocks.0.ff.net.2", "transformer_blocks.1.attn.to_q", "transformer_blocks.1.attn.to_k", "transformer_blocks.1.attn.to_v", "transformer_blocks.1.attn.to_out.0", "transformer_blocks.1.ff.net.0.proj", "transformer_blocks.1.ff.net.2", "transformer_blocks.2.attn.to_q", "transformer_blocks.2.attn.to_k", "transformer_blocks.2.attn.to_v", "transformer_blocks.2.attn.to_out.0", "transformer_blocks.2.ff.net.0.proj", "transformer_blocks.2.ff.net.2", "transformer_blocks.3.attn.to_q", "transformer_blocks.3.attn.to_k", "transformer_blocks.3.attn.to_v", "transformer_blocks.3.attn.to_out.0", "transformer_blocks.3.ff.net.0.proj", "transformer_blocks.3.ff.net.2", "transformer_blocks.4.attn.to_q", "transformer_blocks.4.attn.to_k", "transformer_blocks.4.attn.to_v", "transformer_blocks.4.attn.to_out.0", "transformer_blocks.4.ff.net.0.proj", "transformer_blocks.4.ff.net.2", "transformer_blocks.5.attn.to_q", "transformer_blocks.5.attn.to_k", "transformer_blocks.5.attn.to_v", "transformer_blocks.5.attn.to_out.0", "transformer_blocks.5.ff.net.0.proj", "transformer_blocks.5.ff.net.2", "transformer_blocks.6.attn.to_q", "transformer_blocks.6.attn.to_k", "transformer_blocks.6.attn.to_v", "transformer_blocks.6.attn.to_out.0", "transformer_blocks.6.ff.net.0.proj", "transformer_blocks.6.ff.net.2", "transformer_blocks.7.attn.to_q", "transformer_blocks.7.attn.to_k", "transformer_blocks.7.attn.to_v", "transformer_blocks.7.attn.to_out.0", "transformer_blocks.7.ff.net.0.proj", "transformer_blocks.7.ff.net.2", "transformer_blocks.8.attn.to_q", "transformer_blocks.8.attn.to_k", "transformer_blocks.8.attn.to_v", "transformer_blocks.8.attn.to_out.0", "transformer_blocks.8.ff.net.0.proj", "transformer_blocks.8.ff.net.2", "transformer_blocks.9.attn.to_q", "transformer_blocks.9.attn.to_k", "transformer_blocks.9.attn.to_v", "transformer_blocks.9.attn.to_out.0", "transformer_blocks.9.ff.net.0.proj", "transformer_blocks.9.ff.net.2", "transformer_blocks.10.attn.to_q", "transformer_blocks.10.attn.to_k", "transformer_blocks.10.attn.to_v", "transformer_blocks.10.attn.to_out.0", "transformer_blocks.10.ff.net.0.proj", "transformer_blocks.10.ff.net.2", "transformer_blocks.11.attn.to_q", "transformer_blocks.11.attn.to_k", "transformer_blocks.11.attn.to_v", "transformer_blocks.11.attn.to_out.0", "transformer_blocks.11.ff.net.0.proj", "transformer_blocks.11.ff.net.2", "transformer_blocks.12.attn.to_q", "transformer_blocks.12.attn.to_k", "transformer_blocks.12.attn.to_v", "transformer_blocks.12.attn.to_out.0", "transformer_blocks.12.ff.net.0.proj", "transformer_blocks.12.ff.net.2", "transformer_blocks.13.attn.to_q", "transformer_blocks.13.attn.to_k", "transformer_blocks.13.attn.to_v", "transformer_blocks.13.attn.to_out.0", "transformer_blocks.13.ff.net.0.proj", "transformer_blocks.13.ff.net.2", "transformer_blocks.14.attn.to_q", "transformer_blocks.14.attn.to_k", "transformer_blocks.14.attn.to_v", "transformer_blocks.14.attn.to_out.0", "transformer_blocks.14.ff.net.0.proj", "transformer_blocks.14.ff.net.2", "transformer_blocks.15.attn.to_q", "transformer_blocks.15.attn.to_k", "transformer_blocks.15.attn.to_v", "transformer_blocks.15.attn.to_out.0", "transformer_blocks.15.ff.net.0.proj", "transformer_blocks.15.ff.net.2", "transformer_blocks.16.attn.to_q", "transformer_blocks.16.attn.to_k", "transformer_blocks.16.attn.to_v", "transformer_blocks.16.attn.to_out.0", "transformer_blocks.16.ff.net.0.proj", "transformer_blocks.16.ff.net.2", "transformer_blocks.17.attn.to_q", "transformer_blocks.17.attn.to_k", "transformer_blocks.17.attn.to_v", "transformer_blocks.17.attn.to_out.0", "transformer_blocks.17.ff.net.0.proj", "transformer_blocks.17.ff.net.2", "transformer_blocks.18.attn.to_q", "transformer_blocks.18.attn.to_k", "transformer_blocks.18.attn.to_v", "transformer_blocks.18.attn.to_out.0", "transformer_blocks.18.ff.net.0.proj", "transformer_blocks.18.ff.net.2", "transformer_blocks.19.attn.to_q", "transformer_blocks.19.attn.to_k", "transformer_blocks.19.attn.to_v", "transformer_blocks.19.attn.to_out.0", "transformer_blocks.19.ff.net.0.proj", "transformer_blocks.19.ff.net.2", "transformer_blocks.20.attn.to_q", "transformer_blocks.20.attn.to_k", "transformer_blocks.20.attn.to_v", "transformer_blocks.20.attn.to_out.0", "transformer_blocks.20.ff.net.0.proj", "transformer_blocks.20.ff.net.2", "transformer_blocks.21.attn.to_q", "transformer_blocks.21.attn.to_k", "transformer_blocks.21.attn.to_v", "transformer_blocks.21.attn.to_out.0", "transformer_blocks.21.ff.net.0.proj", "transformer_blocks.21.ff.net.2", "transformer_blocks.22.attn.to_q", "transformer_blocks.22.attn.to_k", "transformer_blocks.22.attn.to_v", "transformer_blocks.22.attn.to_out.0", "transformer_blocks.22.ff.net.0.proj", "transformer_blocks.22.ff.net.2", "transformer_blocks.23.attn.to_q", "transformer_blocks.23.attn.to_k", "transformer_blocks.23.attn.to_v", "transformer_blocks.23.attn.to_out.0", "transformer_blocks.23.ff.net.0.proj", "transformer_blocks.23.ff.net.2", "transformer_blocks.24.attn.to_q", "transformer_blocks.24.attn.to_k", "transformer_blocks.24.attn.to_v", "transformer_blocks.24.attn.to_out.0", "transformer_blocks.24.ff.net.0.proj", "transformer_blocks.24.ff.net.2", "transformer_blocks.25.attn.to_q", "transformer_blocks.25.attn.to_k", "transformer_blocks.25.attn.to_v", "transformer_blocks.25.attn.to_out.0", "transformer_blocks.25.ff.net.0.proj", "transformer_blocks.25.ff.net.2", "transformer_blocks.26.attn.to_q", "transformer_blocks.26.attn.to_k", "transformer_blocks.26.attn.to_v", "transformer_blocks.26.attn.to_out.0", "transformer_blocks.26.ff.net.0.proj", "transformer_blocks.26.ff.net.2", "transformer_blocks.27.attn.to_q", "transformer_blocks.27.attn.to_k", "transformer_blocks.27.attn.to_v", "transformer_blocks.27.attn.to_out.0", "transformer_blocks.27.ff.net.0.proj", "transformer_blocks.27.ff.net.2", "transformer_blocks.28.attn.to_q", "transformer_blocks.28.attn.to_k", "transformer_blocks.28.attn.to_v", "transformer_blocks.28.attn.to_out.0", "transformer_blocks.28.ff.net.0.proj", "transformer_blocks.28.ff.net.2", "transformer_blocks.29.attn.to_q", "transformer_blocks.29.attn.to_k", "transformer_blocks.29.attn.to_v", "transformer_blocks.29.attn.to_out.0", "transformer_blocks.29.ff.net.0.proj", "transformer_blocks.29.ff.net.2", "transformer_blocks.30.attn.to_q", "transformer_blocks.30.attn.to_k", "transformer_blocks.30.attn.to_v", "transformer_blocks.30.attn.to_out.0", "transformer_blocks.30.ff.net.0.proj", "transformer_blocks.30.ff.net.2", "transformer_blocks.31.attn.to_q", "transformer_blocks.31.attn.to_k", "transformer_blocks.31.attn.to_v", "transformer_blocks.31.attn.to_out.0", "transformer_blocks.31.ff.net.0.proj", "transformer_blocks.31.ff.net.2", "transformer_blocks.32.attn.to_q", "transformer_blocks.32.attn.to_k", "transformer_blocks.32.attn.to_v", "transformer_blocks.32.attn.to_out.0", "transformer_blocks.32.ff.net.0.proj", "transformer_blocks.32.ff.net.2", "transformer_blocks.33.attn.to_q", "transformer_blocks.33.attn.to_k", "transformer_blocks.33.attn.to_v", "transformer_blocks.33.attn.to_out.0", "transformer_blocks.33.ff.net.0.proj", "transformer_blocks.33.ff.net.2", "transformer_blocks.34.attn.to_q", "transformer_blocks.34.attn.to_k", "transformer_blocks.34.attn.to_v", "transformer_blocks.34.attn.to_out.0", "transformer_blocks.34.ff.net.0.proj", "transformer_blocks.34.ff.net.2", "transformer_blocks.35.attn.to_q", "transformer_blocks.35.attn.to_k", "transformer_blocks.35.attn.to_v", "transformer_blocks.35.attn.to_out.0", "transformer_blocks.35.ff.net.0.proj", "transformer_blocks.35.ff.net.2", "transformer_blocks.36.attn.to_q", "transformer_blocks.36.attn.to_k", "transformer_blocks.36.attn.to_v", "transformer_blocks.36.attn.to_out.0", "transformer_blocks.36.ff.net.0.proj", "transformer_blocks.36.ff.net.2", "transformer_blocks.37.attn.to_q", "transformer_blocks.37.attn.to_k", "transformer_blocks.37.attn.to_v", "transformer_blocks.37.attn.to_out.0", "transformer_blocks.37.ff.net.0.proj", "transformer_blocks.37.ff.net.2", "transformer_blocks.38.attn.to_q", "transformer_blocks.38.attn.to_k", "transformer_blocks.38.attn.to_v", "transformer_blocks.38.attn.to_out.0", "transformer_blocks.38.ff.net.0.proj", "transformer_blocks.38.ff.net.2", "transformer_blocks.39.attn.to_q", "transformer_blocks.39.attn.to_k", "transformer_blocks.39.attn.to_v", "transformer_blocks.39.attn.to_out.0", "transformer_blocks.39.ff.net.0.proj", "transformer_blocks.39.ff.net.2", "transformer_blocks.40.attn.to_q", "transformer_blocks.40.attn.to_k", "transformer_blocks.40.attn.to_v", "transformer_blocks.40.attn.to_out.0", "transformer_blocks.40.ff.net.0.proj", "transformer_blocks.40.ff.net.2", "transformer_blocks.41.attn.to_q", "transformer_blocks.41.attn.to_k", "transformer_blocks.41.attn.to_v", "transformer_blocks.41.attn.to_out.0", "transformer_blocks.41.ff.net.0.proj", "transformer_blocks.41.ff.net.2", "transformer_blocks.42.attn.to_q", "transformer_blocks.42.attn.to_k", "transformer_blocks.42.attn.to_v", "transformer_blocks.42.attn.to_out.0", "transformer_blocks.42.ff.net.0.proj", "transformer_blocks.42.ff.net.2", "transformer_blocks.43.attn.to_q", "transformer_blocks.43.attn.to_k", "transformer_blocks.43.attn.to_v", "transformer_blocks.43.attn.to_out.0", "transformer_blocks.43.ff.net.0.proj", "transformer_blocks.43.ff.net.2", "transformer_blocks.44.attn.to_q", "transformer_blocks.44.attn.to_k", "transformer_blocks.44.attn.to_v", "transformer_blocks.44.attn.to_out.0", "transformer_blocks.44.ff.net.0.proj", "transformer_blocks.44.ff.net.2", "transformer_blocks.45.attn.to_q", "transformer_blocks.45.attn.to_k", "transformer_blocks.45.attn.to_v", "transformer_blocks.45.attn.to_out.0", "transformer_blocks.45.ff.net.0.proj", "transformer_blocks.45.ff.net.2", "transformer_blocks.46.attn.to_q", "transformer_blocks.46.attn.to_k", "transformer_blocks.46.attn.to_v", "transformer_blocks.46.attn.to_out.0", "transformer_blocks.46.ff.net.0.proj", "transformer_blocks.46.ff.net.2", "transformer_blocks.47.attn.to_q", "transformer_blocks.47.attn.to_k", "transformer_blocks.47.attn.to_v", "transformer_blocks.47.attn.to_out.0", "transformer_blocks.47.ff.net.0.proj", "transformer_blocks.47.ff.net.2", "transformer_blocks.48.attn.to_q", "transformer_blocks.48.attn.to_k", "transformer_blocks.48.attn.to_v", "transformer_blocks.48.attn.to_out.0", "transformer_blocks.48.ff.net.0.proj", "transformer_blocks.48.ff.net.2", "transformer_blocks.49.attn.to_q", "transformer_blocks.49.attn.to_k", "transformer_blocks.49.attn.to_v", "transformer_blocks.49.attn.to_out.0", "transformer_blocks.49.ff.net.0.proj", "transformer_blocks.49.ff.net.2" ], "adaln_int4_modules": [ "transformer_blocks.0.adaln_proj.linear", "transformer_blocks.1.adaln_proj.linear", "transformer_blocks.2.adaln_proj.linear", "transformer_blocks.3.adaln_proj.linear", "transformer_blocks.4.adaln_proj.linear", "transformer_blocks.5.adaln_proj.linear", "transformer_blocks.6.adaln_proj.linear", "transformer_blocks.7.adaln_proj.linear", "transformer_blocks.8.adaln_proj.linear", "transformer_blocks.9.adaln_proj.linear", "transformer_blocks.10.adaln_proj.linear", "transformer_blocks.11.adaln_proj.linear", "transformer_blocks.12.adaln_proj.linear", "transformer_blocks.13.adaln_proj.linear", "transformer_blocks.14.adaln_proj.linear", "transformer_blocks.15.adaln_proj.linear", "transformer_blocks.16.adaln_proj.linear", "transformer_blocks.17.adaln_proj.linear", "transformer_blocks.18.adaln_proj.linear", "transformer_blocks.19.adaln_proj.linear", "transformer_blocks.20.adaln_proj.linear", "transformer_blocks.21.adaln_proj.linear", "transformer_blocks.22.adaln_proj.linear", "transformer_blocks.23.adaln_proj.linear", "transformer_blocks.24.adaln_proj.linear", "transformer_blocks.25.adaln_proj.linear", "transformer_blocks.26.adaln_proj.linear", "transformer_blocks.27.adaln_proj.linear", "transformer_blocks.28.adaln_proj.linear", "transformer_blocks.29.adaln_proj.linear", "transformer_blocks.30.adaln_proj.linear", "transformer_blocks.31.adaln_proj.linear", "transformer_blocks.32.adaln_proj.linear", "transformer_blocks.33.adaln_proj.linear", "transformer_blocks.34.adaln_proj.linear", "transformer_blocks.35.adaln_proj.linear", "transformer_blocks.36.adaln_proj.linear", "transformer_blocks.37.adaln_proj.linear", "transformer_blocks.38.adaln_proj.linear", "transformer_blocks.39.adaln_proj.linear", "transformer_blocks.40.adaln_proj.linear", "transformer_blocks.41.adaln_proj.linear", "transformer_blocks.42.adaln_proj.linear", "transformer_blocks.43.adaln_proj.linear", "transformer_blocks.44.adaln_proj.linear", "transformer_blocks.45.adaln_proj.linear", "transformer_blocks.46.adaln_proj.linear", "transformer_blocks.47.adaln_proj.linear", "transformer_blocks.48.adaln_proj.linear", "transformer_blocks.49.adaln_proj.linear" ], "bf16_linear_modules": [ "proj_in", "audio_proj_in", "context_embedder", "time_embedder.linear_1", "time_embedder.linear_2", "token_refiner.refiner_blocks.0.attn.to_q", "token_refiner.refiner_blocks.0.attn.to_k", "token_refiner.refiner_blocks.0.attn.to_v", "token_refiner.refiner_blocks.0.attn.to_out.0", "token_refiner.refiner_blocks.0.ff.net.0.proj", "token_refiner.refiner_blocks.0.ff.net.2", "token_refiner.refiner_blocks.1.attn.to_q", "token_refiner.refiner_blocks.1.attn.to_k", "token_refiner.refiner_blocks.1.attn.to_v", "token_refiner.refiner_blocks.1.attn.to_out.0", "token_refiner.refiner_blocks.1.ff.net.0.proj", "token_refiner.refiner_blocks.1.ff.net.2", "norm_out.linear", "proj_out", "audio_proj_out" ], "quantized_linear_weight_parameters": 32273203200, "skipped_linear_weight_parameters": 844333056, "linear_weight_parameters": 33117536256, "linear_parameter_coverage": 0.9745049556382073, "packed_module_state_bytes": 16558796800, "full_dequantized_cache_count": 0 }, { "status": "complete", "component": "text_encoder", "framework": "transformers", "class_name": "Qwen3VLForConditionalGeneration", "component_mode": "w4a4", "source_weight_bytes": 66714780128, "artifact_bytes": 19915866369, "load_and_quantize_seconds": 761.9010661011562, "save_seconds": 119.85304131591693, "wall_seconds": 881.9026361107826, "rss_before_bytes": 809992192, "rss_after_bytes": 36594503680, "released_source_tensor_bytes": 62411243520, "source_page_release_failures": 0, "gpu": { "device": "NVIDIA RTX PRO 6000 Blackwell Server Edition", "capability": [ 12, 0 ], "free_bytes": 101319442432, "total_bytes": 101973950464, "allocated_bytes": 196096, "reserved_bytes": 67108864, "peak_allocated_bytes": 46072320, "peak_reserved_bytes": 67108864 }, "orbitquant_module_count": 448, "adaln_int4_module_count": 0, "bf16_linear_module_count": 117, "orbitquant_modules": [ "model.language_model.layers.0.self_attn.q_proj", "model.language_model.layers.0.self_attn.k_proj", "model.language_model.layers.0.self_attn.v_proj", "model.language_model.layers.0.self_attn.o_proj", "model.language_model.layers.0.mlp.gate_proj", "model.language_model.layers.0.mlp.up_proj", "model.language_model.layers.0.mlp.down_proj", "model.language_model.layers.1.self_attn.q_proj", "model.language_model.layers.1.self_attn.k_proj", "model.language_model.layers.1.self_attn.v_proj", "model.language_model.layers.1.self_attn.o_proj", "model.language_model.layers.1.mlp.gate_proj", "model.language_model.layers.1.mlp.up_proj", "model.language_model.layers.1.mlp.down_proj", "model.language_model.layers.2.self_attn.q_proj", "model.language_model.layers.2.self_attn.k_proj", "model.language_model.layers.2.self_attn.v_proj", "model.language_model.layers.2.self_attn.o_proj", "model.language_model.layers.2.mlp.gate_proj", "model.language_model.layers.2.mlp.up_proj", "model.language_model.layers.2.mlp.down_proj", "model.language_model.layers.3.self_attn.q_proj", "model.language_model.layers.3.self_attn.k_proj", "model.language_model.layers.3.self_attn.v_proj", "model.language_model.layers.3.self_attn.o_proj", "model.language_model.layers.3.mlp.gate_proj", "model.language_model.layers.3.mlp.up_proj", "model.language_model.layers.3.mlp.down_proj", "model.language_model.layers.4.self_attn.q_proj", "model.language_model.layers.4.self_attn.k_proj", "model.language_model.layers.4.self_attn.v_proj", "model.language_model.layers.4.self_attn.o_proj", "model.language_model.layers.4.mlp.gate_proj", "model.language_model.layers.4.mlp.up_proj", "model.language_model.layers.4.mlp.down_proj", "model.language_model.layers.5.self_attn.q_proj", "model.language_model.layers.5.self_attn.k_proj", "model.language_model.layers.5.self_attn.v_proj", "model.language_model.layers.5.self_attn.o_proj", "model.language_model.layers.5.mlp.gate_proj", "model.language_model.layers.5.mlp.up_proj", "model.language_model.layers.5.mlp.down_proj", "model.language_model.layers.6.self_attn.q_proj", "model.language_model.layers.6.self_attn.k_proj", "model.language_model.layers.6.self_attn.v_proj", "model.language_model.layers.6.self_attn.o_proj", "model.language_model.layers.6.mlp.gate_proj", "model.language_model.layers.6.mlp.up_proj", "model.language_model.layers.6.mlp.down_proj", "model.language_model.layers.7.self_attn.q_proj", "model.language_model.layers.7.self_attn.k_proj", "model.language_model.layers.7.self_attn.v_proj", "model.language_model.layers.7.self_attn.o_proj", "model.language_model.layers.7.mlp.gate_proj", "model.language_model.layers.7.mlp.up_proj", "model.language_model.layers.7.mlp.down_proj", "model.language_model.layers.8.self_attn.q_proj", "model.language_model.layers.8.self_attn.k_proj", "model.language_model.layers.8.self_attn.v_proj", "model.language_model.layers.8.self_attn.o_proj", "model.language_model.layers.8.mlp.gate_proj", "model.language_model.layers.8.mlp.up_proj", "model.language_model.layers.8.mlp.down_proj", "model.language_model.layers.9.self_attn.q_proj", "model.language_model.layers.9.self_attn.k_proj", "model.language_model.layers.9.self_attn.v_proj", "model.language_model.layers.9.self_attn.o_proj", "model.language_model.layers.9.mlp.gate_proj", "model.language_model.layers.9.mlp.up_proj", "model.language_model.layers.9.mlp.down_proj", "model.language_model.layers.10.self_attn.q_proj", "model.language_model.layers.10.self_attn.k_proj", "model.language_model.layers.10.self_attn.v_proj", "model.language_model.layers.10.self_attn.o_proj", "model.language_model.layers.10.mlp.gate_proj", "model.language_model.layers.10.mlp.up_proj", "model.language_model.layers.10.mlp.down_proj", "model.language_model.layers.11.self_attn.q_proj", "model.language_model.layers.11.self_attn.k_proj", "model.language_model.layers.11.self_attn.v_proj", "model.language_model.layers.11.self_attn.o_proj", "model.language_model.layers.11.mlp.gate_proj", "model.language_model.layers.11.mlp.up_proj", "model.language_model.layers.11.mlp.down_proj", "model.language_model.layers.12.self_attn.q_proj", "model.language_model.layers.12.self_attn.k_proj", "model.language_model.layers.12.self_attn.v_proj", "model.language_model.layers.12.self_attn.o_proj", "model.language_model.layers.12.mlp.gate_proj", "model.language_model.layers.12.mlp.up_proj", "model.language_model.layers.12.mlp.down_proj", "model.language_model.layers.13.self_attn.q_proj", "model.language_model.layers.13.self_attn.k_proj", "model.language_model.layers.13.self_attn.v_proj", "model.language_model.layers.13.self_attn.o_proj", "model.language_model.layers.13.mlp.gate_proj", "model.language_model.layers.13.mlp.up_proj", "model.language_model.layers.13.mlp.down_proj", "model.language_model.layers.14.self_attn.q_proj", "model.language_model.layers.14.self_attn.k_proj", "model.language_model.layers.14.self_attn.v_proj", "model.language_model.layers.14.self_attn.o_proj", "model.language_model.layers.14.mlp.gate_proj", "model.language_model.layers.14.mlp.up_proj", "model.language_model.layers.14.mlp.down_proj", "model.language_model.layers.15.self_attn.q_proj", "model.language_model.layers.15.self_attn.k_proj", "model.language_model.layers.15.self_attn.v_proj", "model.language_model.layers.15.self_attn.o_proj", "model.language_model.layers.15.mlp.gate_proj", "model.language_model.layers.15.mlp.up_proj", "model.language_model.layers.15.mlp.down_proj", "model.language_model.layers.16.self_attn.q_proj", "model.language_model.layers.16.self_attn.k_proj", "model.language_model.layers.16.self_attn.v_proj", "model.language_model.layers.16.self_attn.o_proj", "model.language_model.layers.16.mlp.gate_proj", "model.language_model.layers.16.mlp.up_proj", "model.language_model.layers.16.mlp.down_proj", "model.language_model.layers.17.self_attn.q_proj", "model.language_model.layers.17.self_attn.k_proj", "model.language_model.layers.17.self_attn.v_proj", "model.language_model.layers.17.self_attn.o_proj", "model.language_model.layers.17.mlp.gate_proj", "model.language_model.layers.17.mlp.up_proj", "model.language_model.layers.17.mlp.down_proj", "model.language_model.layers.18.self_attn.q_proj", "model.language_model.layers.18.self_attn.k_proj", "model.language_model.layers.18.self_attn.v_proj", "model.language_model.layers.18.self_attn.o_proj", "model.language_model.layers.18.mlp.gate_proj", "model.language_model.layers.18.mlp.up_proj", "model.language_model.layers.18.mlp.down_proj", "model.language_model.layers.19.self_attn.q_proj", "model.language_model.layers.19.self_attn.k_proj", "model.language_model.layers.19.self_attn.v_proj", "model.language_model.layers.19.self_attn.o_proj", "model.language_model.layers.19.mlp.gate_proj", "model.language_model.layers.19.mlp.up_proj", "model.language_model.layers.19.mlp.down_proj", "model.language_model.layers.20.self_attn.q_proj", "model.language_model.layers.20.self_attn.k_proj", "model.language_model.layers.20.self_attn.v_proj", "model.language_model.layers.20.self_attn.o_proj", "model.language_model.layers.20.mlp.gate_proj", "model.language_model.layers.20.mlp.up_proj", "model.language_model.layers.20.mlp.down_proj", "model.language_model.layers.21.self_attn.q_proj", "model.language_model.layers.21.self_attn.k_proj", "model.language_model.layers.21.self_attn.v_proj", "model.language_model.layers.21.self_attn.o_proj", "model.language_model.layers.21.mlp.gate_proj", "model.language_model.layers.21.mlp.up_proj", "model.language_model.layers.21.mlp.down_proj", "model.language_model.layers.22.self_attn.q_proj", "model.language_model.layers.22.self_attn.k_proj", "model.language_model.layers.22.self_attn.v_proj", "model.language_model.layers.22.self_attn.o_proj", "model.language_model.layers.22.mlp.gate_proj", "model.language_model.layers.22.mlp.up_proj", "model.language_model.layers.22.mlp.down_proj", "model.language_model.layers.23.self_attn.q_proj", "model.language_model.layers.23.self_attn.k_proj", "model.language_model.layers.23.self_attn.v_proj", "model.language_model.layers.23.self_attn.o_proj", "model.language_model.layers.23.mlp.gate_proj", "model.language_model.layers.23.mlp.up_proj", "model.language_model.layers.23.mlp.down_proj", "model.language_model.layers.24.self_attn.q_proj", "model.language_model.layers.24.self_attn.k_proj", "model.language_model.layers.24.self_attn.v_proj", "model.language_model.layers.24.self_attn.o_proj", "model.language_model.layers.24.mlp.gate_proj", "model.language_model.layers.24.mlp.up_proj", "model.language_model.layers.24.mlp.down_proj", "model.language_model.layers.25.self_attn.q_proj", "model.language_model.layers.25.self_attn.k_proj", "model.language_model.layers.25.self_attn.v_proj", "model.language_model.layers.25.self_attn.o_proj", "model.language_model.layers.25.mlp.gate_proj", "model.language_model.layers.25.mlp.up_proj", "model.language_model.layers.25.mlp.down_proj", "model.language_model.layers.26.self_attn.q_proj", "model.language_model.layers.26.self_attn.k_proj", "model.language_model.layers.26.self_attn.v_proj", "model.language_model.layers.26.self_attn.o_proj", "model.language_model.layers.26.mlp.gate_proj", "model.language_model.layers.26.mlp.up_proj", "model.language_model.layers.26.mlp.down_proj", "model.language_model.layers.27.self_attn.q_proj", "model.language_model.layers.27.self_attn.k_proj", "model.language_model.layers.27.self_attn.v_proj", "model.language_model.layers.27.self_attn.o_proj", "model.language_model.layers.27.mlp.gate_proj", "model.language_model.layers.27.mlp.up_proj", "model.language_model.layers.27.mlp.down_proj", "model.language_model.layers.28.self_attn.q_proj", "model.language_model.layers.28.self_attn.k_proj", "model.language_model.layers.28.self_attn.v_proj", "model.language_model.layers.28.self_attn.o_proj", "model.language_model.layers.28.mlp.gate_proj", "model.language_model.layers.28.mlp.up_proj", "model.language_model.layers.28.mlp.down_proj", "model.language_model.layers.29.self_attn.q_proj", "model.language_model.layers.29.self_attn.k_proj", "model.language_model.layers.29.self_attn.v_proj", "model.language_model.layers.29.self_attn.o_proj", "model.language_model.layers.29.mlp.gate_proj", "model.language_model.layers.29.mlp.up_proj", "model.language_model.layers.29.mlp.down_proj", "model.language_model.layers.30.self_attn.q_proj", "model.language_model.layers.30.self_attn.k_proj", "model.language_model.layers.30.self_attn.v_proj", "model.language_model.layers.30.self_attn.o_proj", "model.language_model.layers.30.mlp.gate_proj", "model.language_model.layers.30.mlp.up_proj", "model.language_model.layers.30.mlp.down_proj", "model.language_model.layers.31.self_attn.q_proj", "model.language_model.layers.31.self_attn.k_proj", "model.language_model.layers.31.self_attn.v_proj", "model.language_model.layers.31.self_attn.o_proj", "model.language_model.layers.31.mlp.gate_proj", "model.language_model.layers.31.mlp.up_proj", "model.language_model.layers.31.mlp.down_proj", "model.language_model.layers.32.self_attn.q_proj", "model.language_model.layers.32.self_attn.k_proj", "model.language_model.layers.32.self_attn.v_proj", "model.language_model.layers.32.self_attn.o_proj", "model.language_model.layers.32.mlp.gate_proj", "model.language_model.layers.32.mlp.up_proj", "model.language_model.layers.32.mlp.down_proj", "model.language_model.layers.33.self_attn.q_proj", "model.language_model.layers.33.self_attn.k_proj", "model.language_model.layers.33.self_attn.v_proj", "model.language_model.layers.33.self_attn.o_proj", "model.language_model.layers.33.mlp.gate_proj", "model.language_model.layers.33.mlp.up_proj", "model.language_model.layers.33.mlp.down_proj", "model.language_model.layers.34.self_attn.q_proj", "model.language_model.layers.34.self_attn.k_proj", "model.language_model.layers.34.self_attn.v_proj", "model.language_model.layers.34.self_attn.o_proj", "model.language_model.layers.34.mlp.gate_proj", "model.language_model.layers.34.mlp.up_proj", "model.language_model.layers.34.mlp.down_proj", "model.language_model.layers.35.self_attn.q_proj", "model.language_model.layers.35.self_attn.k_proj", "model.language_model.layers.35.self_attn.v_proj", "model.language_model.layers.35.self_attn.o_proj", "model.language_model.layers.35.mlp.gate_proj", "model.language_model.layers.35.mlp.up_proj", "model.language_model.layers.35.mlp.down_proj", "model.language_model.layers.36.self_attn.q_proj", "model.language_model.layers.36.self_attn.k_proj", "model.language_model.layers.36.self_attn.v_proj", "model.language_model.layers.36.self_attn.o_proj", "model.language_model.layers.36.mlp.gate_proj", "model.language_model.layers.36.mlp.up_proj", "model.language_model.layers.36.mlp.down_proj", "model.language_model.layers.37.self_attn.q_proj", "model.language_model.layers.37.self_attn.k_proj", "model.language_model.layers.37.self_attn.v_proj", "model.language_model.layers.37.self_attn.o_proj", "model.language_model.layers.37.mlp.gate_proj", "model.language_model.layers.37.mlp.up_proj", "model.language_model.layers.37.mlp.down_proj", "model.language_model.layers.38.self_attn.q_proj", "model.language_model.layers.38.self_attn.k_proj", "model.language_model.layers.38.self_attn.v_proj", "model.language_model.layers.38.self_attn.o_proj", "model.language_model.layers.38.mlp.gate_proj", "model.language_model.layers.38.mlp.up_proj", "model.language_model.layers.38.mlp.down_proj", "model.language_model.layers.39.self_attn.q_proj", "model.language_model.layers.39.self_attn.k_proj", "model.language_model.layers.39.self_attn.v_proj", "model.language_model.layers.39.self_attn.o_proj", "model.language_model.layers.39.mlp.gate_proj", "model.language_model.layers.39.mlp.up_proj", "model.language_model.layers.39.mlp.down_proj", "model.language_model.layers.40.self_attn.q_proj", "model.language_model.layers.40.self_attn.k_proj", "model.language_model.layers.40.self_attn.v_proj", "model.language_model.layers.40.self_attn.o_proj", "model.language_model.layers.40.mlp.gate_proj", "model.language_model.layers.40.mlp.up_proj", "model.language_model.layers.40.mlp.down_proj", "model.language_model.layers.41.self_attn.q_proj", "model.language_model.layers.41.self_attn.k_proj", "model.language_model.layers.41.self_attn.v_proj", "model.language_model.layers.41.self_attn.o_proj", "model.language_model.layers.41.mlp.gate_proj", "model.language_model.layers.41.mlp.up_proj", "model.language_model.layers.41.mlp.down_proj", "model.language_model.layers.42.self_attn.q_proj", "model.language_model.layers.42.self_attn.k_proj", "model.language_model.layers.42.self_attn.v_proj", "model.language_model.layers.42.self_attn.o_proj", "model.language_model.layers.42.mlp.gate_proj", "model.language_model.layers.42.mlp.up_proj", "model.language_model.layers.42.mlp.down_proj", "model.language_model.layers.43.self_attn.q_proj", "model.language_model.layers.43.self_attn.k_proj", "model.language_model.layers.43.self_attn.v_proj", "model.language_model.layers.43.self_attn.o_proj", "model.language_model.layers.43.mlp.gate_proj", "model.language_model.layers.43.mlp.up_proj", "model.language_model.layers.43.mlp.down_proj", "model.language_model.layers.44.self_attn.q_proj", "model.language_model.layers.44.self_attn.k_proj", "model.language_model.layers.44.self_attn.v_proj", "model.language_model.layers.44.self_attn.o_proj", "model.language_model.layers.44.mlp.gate_proj", "model.language_model.layers.44.mlp.up_proj", "model.language_model.layers.44.mlp.down_proj", "model.language_model.layers.45.self_attn.q_proj", "model.language_model.layers.45.self_attn.k_proj", "model.language_model.layers.45.self_attn.v_proj", "model.language_model.layers.45.self_attn.o_proj", "model.language_model.layers.45.mlp.gate_proj", "model.language_model.layers.45.mlp.up_proj", "model.language_model.layers.45.mlp.down_proj", "model.language_model.layers.46.self_attn.q_proj", "model.language_model.layers.46.self_attn.k_proj", "model.language_model.layers.46.self_attn.v_proj", "model.language_model.layers.46.self_attn.o_proj", "model.language_model.layers.46.mlp.gate_proj", "model.language_model.layers.46.mlp.up_proj", "model.language_model.layers.46.mlp.down_proj", "model.language_model.layers.47.self_attn.q_proj", "model.language_model.layers.47.self_attn.k_proj", "model.language_model.layers.47.self_attn.v_proj", "model.language_model.layers.47.self_attn.o_proj", "model.language_model.layers.47.mlp.gate_proj", "model.language_model.layers.47.mlp.up_proj", "model.language_model.layers.47.mlp.down_proj", "model.language_model.layers.48.self_attn.q_proj", "model.language_model.layers.48.self_attn.k_proj", "model.language_model.layers.48.self_attn.v_proj", "model.language_model.layers.48.self_attn.o_proj", "model.language_model.layers.48.mlp.gate_proj", "model.language_model.layers.48.mlp.up_proj", "model.language_model.layers.48.mlp.down_proj", "model.language_model.layers.49.self_attn.q_proj", "model.language_model.layers.49.self_attn.k_proj", "model.language_model.layers.49.self_attn.v_proj", "model.language_model.layers.49.self_attn.o_proj", "model.language_model.layers.49.mlp.gate_proj", "model.language_model.layers.49.mlp.up_proj", "model.language_model.layers.49.mlp.down_proj", "model.language_model.layers.50.self_attn.q_proj", "model.language_model.layers.50.self_attn.k_proj", "model.language_model.layers.50.self_attn.v_proj", "model.language_model.layers.50.self_attn.o_proj", "model.language_model.layers.50.mlp.gate_proj", "model.language_model.layers.50.mlp.up_proj", "model.language_model.layers.50.mlp.down_proj", "model.language_model.layers.51.self_attn.q_proj", "model.language_model.layers.51.self_attn.k_proj", "model.language_model.layers.51.self_attn.v_proj", "model.language_model.layers.51.self_attn.o_proj", "model.language_model.layers.51.mlp.gate_proj", "model.language_model.layers.51.mlp.up_proj", "model.language_model.layers.51.mlp.down_proj", "model.language_model.layers.52.self_attn.q_proj", "model.language_model.layers.52.self_attn.k_proj", "model.language_model.layers.52.self_attn.v_proj", "model.language_model.layers.52.self_attn.o_proj", "model.language_model.layers.52.mlp.gate_proj", "model.language_model.layers.52.mlp.up_proj", "model.language_model.layers.52.mlp.down_proj", "model.language_model.layers.53.self_attn.q_proj", "model.language_model.layers.53.self_attn.k_proj", "model.language_model.layers.53.self_attn.v_proj", "model.language_model.layers.53.self_attn.o_proj", "model.language_model.layers.53.mlp.gate_proj", "model.language_model.layers.53.mlp.up_proj", "model.language_model.layers.53.mlp.down_proj", "model.language_model.layers.54.self_attn.q_proj", "model.language_model.layers.54.self_attn.k_proj", "model.language_model.layers.54.self_attn.v_proj", "model.language_model.layers.54.self_attn.o_proj", "model.language_model.layers.54.mlp.gate_proj", "model.language_model.layers.54.mlp.up_proj", "model.language_model.layers.54.mlp.down_proj", "model.language_model.layers.55.self_attn.q_proj", "model.language_model.layers.55.self_attn.k_proj", "model.language_model.layers.55.self_attn.v_proj", "model.language_model.layers.55.self_attn.o_proj", "model.language_model.layers.55.mlp.gate_proj", "model.language_model.layers.55.mlp.up_proj", "model.language_model.layers.55.mlp.down_proj", "model.language_model.layers.56.self_attn.q_proj", "model.language_model.layers.56.self_attn.k_proj", "model.language_model.layers.56.self_attn.v_proj", "model.language_model.layers.56.self_attn.o_proj", "model.language_model.layers.56.mlp.gate_proj", "model.language_model.layers.56.mlp.up_proj", "model.language_model.layers.56.mlp.down_proj", "model.language_model.layers.57.self_attn.q_proj", "model.language_model.layers.57.self_attn.k_proj", "model.language_model.layers.57.self_attn.v_proj", "model.language_model.layers.57.self_attn.o_proj", "model.language_model.layers.57.mlp.gate_proj", "model.language_model.layers.57.mlp.up_proj", "model.language_model.layers.57.mlp.down_proj", "model.language_model.layers.58.self_attn.q_proj", "model.language_model.layers.58.self_attn.k_proj", "model.language_model.layers.58.self_attn.v_proj", "model.language_model.layers.58.self_attn.o_proj", "model.language_model.layers.58.mlp.gate_proj", "model.language_model.layers.58.mlp.up_proj", "model.language_model.layers.58.mlp.down_proj", "model.language_model.layers.59.self_attn.q_proj", "model.language_model.layers.59.self_attn.k_proj", "model.language_model.layers.59.self_attn.v_proj", "model.language_model.layers.59.self_attn.o_proj", "model.language_model.layers.59.mlp.gate_proj", "model.language_model.layers.59.mlp.up_proj", "model.language_model.layers.59.mlp.down_proj", "model.language_model.layers.60.self_attn.q_proj", "model.language_model.layers.60.self_attn.k_proj", "model.language_model.layers.60.self_attn.v_proj", "model.language_model.layers.60.self_attn.o_proj", "model.language_model.layers.60.mlp.gate_proj", "model.language_model.layers.60.mlp.up_proj", "model.language_model.layers.60.mlp.down_proj", "model.language_model.layers.61.self_attn.q_proj", "model.language_model.layers.61.self_attn.k_proj", "model.language_model.layers.61.self_attn.v_proj", "model.language_model.layers.61.self_attn.o_proj", "model.language_model.layers.61.mlp.gate_proj", "model.language_model.layers.61.mlp.up_proj", "model.language_model.layers.61.mlp.down_proj", "model.language_model.layers.62.self_attn.q_proj", "model.language_model.layers.62.self_attn.k_proj", "model.language_model.layers.62.self_attn.v_proj", "model.language_model.layers.62.self_attn.o_proj", "model.language_model.layers.62.mlp.gate_proj", "model.language_model.layers.62.mlp.up_proj", "model.language_model.layers.62.mlp.down_proj", "model.language_model.layers.63.self_attn.q_proj", "model.language_model.layers.63.self_attn.k_proj", "model.language_model.layers.63.self_attn.v_proj", "model.language_model.layers.63.self_attn.o_proj", "model.language_model.layers.63.mlp.gate_proj", "model.language_model.layers.63.mlp.up_proj", "model.language_model.layers.63.mlp.down_proj" ], "adaln_int4_modules": [], "bf16_linear_modules": [ "model.visual.blocks.0.attn.qkv", "model.visual.blocks.0.attn.proj", "model.visual.blocks.0.mlp.linear_fc1", "model.visual.blocks.0.mlp.linear_fc2", "model.visual.blocks.1.attn.qkv", "model.visual.blocks.1.attn.proj", "model.visual.blocks.1.mlp.linear_fc1", "model.visual.blocks.1.mlp.linear_fc2", "model.visual.blocks.2.attn.qkv", "model.visual.blocks.2.attn.proj", "model.visual.blocks.2.mlp.linear_fc1", "model.visual.blocks.2.mlp.linear_fc2", "model.visual.blocks.3.attn.qkv", "model.visual.blocks.3.attn.proj", "model.visual.blocks.3.mlp.linear_fc1", "model.visual.blocks.3.mlp.linear_fc2", "model.visual.blocks.4.attn.qkv", "model.visual.blocks.4.attn.proj", "model.visual.blocks.4.mlp.linear_fc1", "model.visual.blocks.4.mlp.linear_fc2", "model.visual.blocks.5.attn.qkv", "model.visual.blocks.5.attn.proj", "model.visual.blocks.5.mlp.linear_fc1", "model.visual.blocks.5.mlp.linear_fc2", "model.visual.blocks.6.attn.qkv", "model.visual.blocks.6.attn.proj", "model.visual.blocks.6.mlp.linear_fc1", "model.visual.blocks.6.mlp.linear_fc2", "model.visual.blocks.7.attn.qkv", "model.visual.blocks.7.attn.proj", "model.visual.blocks.7.mlp.linear_fc1", "model.visual.blocks.7.mlp.linear_fc2", "model.visual.blocks.8.attn.qkv", "model.visual.blocks.8.attn.proj", "model.visual.blocks.8.mlp.linear_fc1", "model.visual.blocks.8.mlp.linear_fc2", "model.visual.blocks.9.attn.qkv", "model.visual.blocks.9.attn.proj", "model.visual.blocks.9.mlp.linear_fc1", "model.visual.blocks.9.mlp.linear_fc2", "model.visual.blocks.10.attn.qkv", "model.visual.blocks.10.attn.proj", "model.visual.blocks.10.mlp.linear_fc1", "model.visual.blocks.10.mlp.linear_fc2", "model.visual.blocks.11.attn.qkv", "model.visual.blocks.11.attn.proj", "model.visual.blocks.11.mlp.linear_fc1", "model.visual.blocks.11.mlp.linear_fc2", "model.visual.blocks.12.attn.qkv", "model.visual.blocks.12.attn.proj", "model.visual.blocks.12.mlp.linear_fc1", "model.visual.blocks.12.mlp.linear_fc2", "model.visual.blocks.13.attn.qkv", "model.visual.blocks.13.attn.proj", "model.visual.blocks.13.mlp.linear_fc1", "model.visual.blocks.13.mlp.linear_fc2", "model.visual.blocks.14.attn.qkv", "model.visual.blocks.14.attn.proj", "model.visual.blocks.14.mlp.linear_fc1", "model.visual.blocks.14.mlp.linear_fc2", "model.visual.blocks.15.attn.qkv", "model.visual.blocks.15.attn.proj", "model.visual.blocks.15.mlp.linear_fc1", "model.visual.blocks.15.mlp.linear_fc2", "model.visual.blocks.16.attn.qkv", "model.visual.blocks.16.attn.proj", "model.visual.blocks.16.mlp.linear_fc1", "model.visual.blocks.16.mlp.linear_fc2", "model.visual.blocks.17.attn.qkv", "model.visual.blocks.17.attn.proj", "model.visual.blocks.17.mlp.linear_fc1", "model.visual.blocks.17.mlp.linear_fc2", "model.visual.blocks.18.attn.qkv", "model.visual.blocks.18.attn.proj", "model.visual.blocks.18.mlp.linear_fc1", "model.visual.blocks.18.mlp.linear_fc2", "model.visual.blocks.19.attn.qkv", "model.visual.blocks.19.attn.proj", "model.visual.blocks.19.mlp.linear_fc1", "model.visual.blocks.19.mlp.linear_fc2", "model.visual.blocks.20.attn.qkv", "model.visual.blocks.20.attn.proj", "model.visual.blocks.20.mlp.linear_fc1", "model.visual.blocks.20.mlp.linear_fc2", "model.visual.blocks.21.attn.qkv", "model.visual.blocks.21.attn.proj", "model.visual.blocks.21.mlp.linear_fc1", "model.visual.blocks.21.mlp.linear_fc2", "model.visual.blocks.22.attn.qkv", "model.visual.blocks.22.attn.proj", "model.visual.blocks.22.mlp.linear_fc1", "model.visual.blocks.22.mlp.linear_fc2", "model.visual.blocks.23.attn.qkv", "model.visual.blocks.23.attn.proj", "model.visual.blocks.23.mlp.linear_fc1", "model.visual.blocks.23.mlp.linear_fc2", "model.visual.blocks.24.attn.qkv", "model.visual.blocks.24.attn.proj", "model.visual.blocks.24.mlp.linear_fc1", "model.visual.blocks.24.mlp.linear_fc2", "model.visual.blocks.25.attn.qkv", "model.visual.blocks.25.attn.proj", "model.visual.blocks.25.mlp.linear_fc1", "model.visual.blocks.25.mlp.linear_fc2", "model.visual.blocks.26.attn.qkv", "model.visual.blocks.26.attn.proj", "model.visual.blocks.26.mlp.linear_fc1", "model.visual.blocks.26.mlp.linear_fc2", "model.visual.merger.linear_fc1", "model.visual.merger.linear_fc2", "model.visual.deepstack_merger_list.0.linear_fc1", "model.visual.deepstack_merger_list.0.linear_fc2", "model.visual.deepstack_merger_list.1.linear_fc1", "model.visual.deepstack_merger_list.1.linear_fc2", "model.visual.deepstack_merger_list.2.linear_fc1", "model.visual.deepstack_merger_list.2.linear_fc2", "lm_head" ], "quantized_linear_weight_parameters": 31205621760, "skipped_linear_weight_parameters": 1368289280, "linear_weight_parameters": 32573911040, "linear_parameter_coverage": 0.9579943201072855, "packed_module_state_bytes": 15611985920, "full_dequantized_cache_count": 0 }, { "status": "complete", "component": "vae", "framework": "diffusers", "class_name": "AutoencoderKLMiniMaxH3", "component_mode": "source_copy", "source_weight_bytes": 10415475936, "artifact_bytes": 10415635127, "load_and_quantize_seconds": 0.0, "save_seconds": 0.0, "wall_seconds": 187.24781295564026, "orbitquant_module_count": 0, "adaln_int4_module_count": 0, "bf16_linear_module_count": 0, "orbitquant_modules": [], "adaln_int4_modules": [], "bf16_linear_modules": [], "quantized_linear_weight_parameters": 0, "skipped_linear_weight_parameters": 0, "linear_weight_parameters": 0, "linear_parameter_coverage": 0.0, "packed_module_state_bytes": 0, "full_dequantized_cache_count": 0, "released_source_tensor_bytes": null, "source_page_release_failures": null, "gpu": { "device": "NVIDIA RTX PRO 6000 Blackwell Server Edition", "capability": [ 12, 0 ], "free_bytes": 101388648448, "total_bytes": 101973950464, "allocated_bytes": 0, "reserved_bytes": 0, "peak_allocated_bytes": 0, "peak_reserved_bytes": 0 } }, { "status": "complete", "component": "audio_vae", "framework": "diffusers", "class_name": "AutoencoderKLMiniMaxH3Audio", "component_mode": "source_copy", "source_weight_bytes": null, "artifact_bytes": 605431611, "load_and_quantize_seconds": 0.0, "save_seconds": 0.0, "wall_seconds": 35.21525437710807, "orbitquant_module_count": 0, "adaln_int4_module_count": 0, "bf16_linear_module_count": 0, "orbitquant_modules": [], "adaln_int4_modules": [], "bf16_linear_modules": [], "quantized_linear_weight_parameters": 0, "skipped_linear_weight_parameters": 0, "linear_weight_parameters": 0, "linear_parameter_coverage": 0.0, "packed_module_state_bytes": 0, "full_dequantized_cache_count": 0, "released_source_tensor_bytes": null, "source_page_release_failures": null, "gpu": { "device": "NVIDIA RTX PRO 6000 Blackwell Server Edition", "capability": [ 12, 0 ], "free_bytes": 101388648448, "total_bytes": 101973950464, "allocated_bytes": 0, "reserved_bytes": 0, "peak_allocated_bytes": 0, "peak_reserved_bytes": 0 } } ], "totals": { "source_weight_bytes": 209691116224, "artifact_bytes": 67503669349, "quantized_linear_weight_parameters": 95752028160, "skipped_linear_weight_parameters": 3056955392, "orbitquant_module_count": 1048, "adaln_int4_module_count": 100, "bf16_linear_module_count": 157, "linear_parameter_coverage": 0.9690619690426101 }, "validated_runtime": { "text_encoder": "w4a4_auto_fused_cuda_then_cpu_offload", "transformer": "native_packed_w4a4_bf16_compute", "transformer_ref": "native_packed_w4a4_bf16_compute", "vae": "source_fp32_separate_decode", "audio_vae": "source_fp32_separate_decode", "num_inference_steps": 24, "model_evaluations": 23, "default_inference_profile": "balanced", "inference_profiles": { "balanced": "streamed_leaf_group_offload_with_12_gib_allocator_cap", "speed": "resident_selected_transformer", "minimum_vram": "low_cpu_memory_streamed_leaf_group_offload_with_8_gib_allocator_cap" }, "exact_int8_weight_cache": false, "attention_backend": "native_auto_torch_flash_sdpa" }, "validated_runtime_provenance": { "orbitquant_version": "0.9.2", "orbitquant_revision": "cd58b4ecf77f22b8c4116b3d0b7d4af258e16ba3", "orbitquant_requirement": "orbitquant[hf,kernels]>=0.9.2,<0.10", "diffusers_revision": "abc5e9bf71fd38f53cd471bc3acaa84bc5ecbfdc" } }