{ "arch_id": "qwen3-next-mtp", "artifact_role": "forge-local", "base_trunk": "/Users/yang.wang/models/qwen3.8-27b-src", "exactness_baseline": {}, "forge_provenance": { "forge_inputs": { "mtp_source_path": "/Users/yang.wang/models/qwen3.8-27b-src", "trunk_path": "/Users/yang.wang/Documents/MTPLX/models/Qwen3.8-27B-MTPLX-4bit" }, "forge_recipe": { "body_bits": 4, "body_group_size": 64, "body_mode": "affine", "mtp_policy": "keep_bf16" }, "forged_at": "2026-08-24T00:28:10+09:00", "forged_locally": true, "mtp_contract": { "base_hidden_variant": "post_norm", "concat_order": "embedding_hidden", "hidden_variant": "post_norm", "mtp_position_mode": "local", "mtp_quant_group_size": 64, "mtp_quant_mode": "affine" }, "mtplx_version": "2.9.1", "published_to_hf": null, "source_format": "bf16_native", "source_repo": "/Users/yang.wang/models/qwen3.8-27b-src", "source_sha": null }, "mtp_contract": { "base_hidden_variant": "post_norm", "concat_order": "embedding_hidden", "hidden_variant": "post_norm", "mtp_position_mode": "local", "mtp_quant_group_size": 64, "mtp_quant_mode": "affine" }, "mtp_depth_max": 3, "mtp_sidecar": "mtp.safetensors", "mtplx_version": "2.9.1", "recommended_profile": "sustained", "sampler": { "temperature": 0.6, "top_k": 20, "top_p": 0.95 }, "speed_evidence": { "acceptance_by_depth": [ 1.0, 1.0, 0.8 ], "acceptance_collapsed": [], "artifact_fingerprint": "sha256:caa118baa7455f6e83aba9079cbba16ed04c375ffd5b987d9f45aecac19a6e6a", "depth": 3, "failure_reasons": [], "forge_verify_rows": [ { "acceptance_by_position": [], "depth": 0, "finish_reasons": { "length": 1 }, "hit_token_budget": true, "hit_token_budget_count": 1, "multiplier_vs_ar": 1.0, "quality_passed": true, "tok_s": 21.744767277204435, "verify_time_s": 1.9631269170204177 }, { "acceptance_by_position": [ 1.0 ], "depth": 1, "finish_reasons": { "length": 1 }, "hit_token_budget": true, "hit_token_budget_count": 1, "multiplier_vs_ar": 1.7178727553803572, "quality_passed": true, "tok_s": 37.35474327759581, "verify_time_s": 0.8072494564112276 }, { "acceptance_by_position": [ 1.0, 1.0 ], "depth": 2, "finish_reasons": { "length": 1 }, "hit_token_budget": true, "hit_token_budget_count": 1, "multiplier_vs_ar": 1.7711165965234528, "quality_passed": true, "tok_s": 38.512518212196866, "verify_time_s": 0.7674681238131598 }, { "acceptance_by_position": [ 1.0, 1.0, 0.8 ], "depth": 3, "finish_reasons": { "length": 1 }, "hit_token_budget": true, "hit_token_budget_count": 1, "multiplier_vs_ar": 2.295863870102533, "quality_passed": true, "tok_s": 49.92302555552149, "verify_time_s": 0.557183044264093 } ], "greedy_diagnostic": { "tok_s": 21.744767277204435 }, "quality_rejected": [], "tok_s": [ 49.92302555552149 ], "verdict": "mtp_depth_wins" }, "verified_on": { "hardware": "macOS-15.7.3-arm64-arm-64bit", "machine_arch": "arm64", "macos": "15.7.3", "model": "Qwen3.8-27B-MTPLX-4bit", "timestamp": "2026-08-24T00:28:10+09:00" }, "vision": { "prefix": "vision_tower.", "shards": [ "model-vision.safetensors" ], "tensor_count": 333 }, "mtp_file": "mtp.safetensors", "remaining_q4_to_q3": { "selected_leaf_types": [ "in_proj_z" ], "selected_layers": [ 2, 4, 5, 9, 10, 16, 17, 20, 21, 22, 24, 25, 29, 30, 32, 34, 36, 37, 38, 40, 41, 44, 45, 48, 49, 50, 53, 56, 60, 61, 62 ], "selected_module_count": 31, "group_size": 64, "mtp_sidecar_unchanged": true } }