{ "schema_version": 1, "repository": "PocketAiHub/Qwen3.8-9B-MLX", "lineage": "regular", "source_repository": "empero-ai/Qwen3.8-9B", "source_revision": "0934f3d2327ff2df2197495278c4c46ae5a56bd9", "base_model": "Qwen/Qwen3.5-9B", "runtime": { "mlx": "0.32.0", "mlx_vlm": "0.6.8" }, "variants": [ { "name": "4bit", "path": "4bit", "precision": "4-bit", "validation": { "schema_version": 1, "repository": "PocketAiHub/Qwen3.8-9B-MLX", "lineage": "regular", "source_repository": "empero-ai/Qwen3.8-9B", "source_revision": "0934f3d2327ff2df2197495278c4c46ae5a56bd9", "base_model": "Qwen/Qwen3.5-9B", "runtime": { "mlx": "0.32.0", "mlx_vlm": "0.6.8" }, "format": { "precision": "4-bit", "language_quantization": { "mode": "affine", "bits": 4, "group_size": 64 }, "vision_tower": "BF16", "native_mtp_included": false, "shard_count": 2, "source_manifest": "workspace/exports/mlx/pocketai-qwen3.8-9b-mlx-4bit/artifact-manifest.json", "source_manifest_sha256": "02a89f998c02e0b0d011eed3cd69427b4041720e5554819f0676998ebb2973e1" }, "evidence": { "smoke": { "report": "workspace/runs/qwen3.8-9b-regular-benchmarks/4bit/runtime-smoke.json", "report_sha256": "91ac69d715bee134187e498842e314f5b28c381d069e8a16f2d16652f5e50d49", "result": { "passed": true, "text_passed": true, "vision_passed": true, "peak_mlx_memory_gb": 7.022197602 } }, "performance": { "report": "workspace/runs/qwen3.8-9b-regular-benchmarks/4bit-4k/report.json", "report_sha256": "dd82d29a492b1a1ce3f66540d711e9bb117fcd80b6391ef55de646418b02f638", "result": { "passed": true, "formatted_tokens": 4096, "expected": "COBALT-7319", "prefill_tokens_per_second": 3197.327651141933, "decode_tokens_per_second": 100.27767318668539, "peak_mlx_bytes": 6969058358, "kv_bits": null } }, "feature": { "report": "workspace/runs/qwen3.8-9b-release/regular-4bit-feature-64k.json", "report_sha256": "0f0c9d871812ad179e29b7c0bc4a8ea1c09bf980f09b3bb5eea540fa30fac07d", "result": { "quality": { "passed": true, "pass_count": 12, "case_count": 12 }, "tool_calling": { "passed": true, "pass_count": 8, "case_count": 8 }, "temporal_video": { "passed": true, "expected": "red->blue", "actual": "red->blue" }, "long_context": { "passed": true, "formatted_tokens": 65545, "expected": "COBALT-7319", "actual": "COBALT-7319", "peak_memory_gb": 15.190558278 } } } }, "release_status": "experimental-community-family-release", "variant_path": "4bit" } }, { "name": "8bit", "path": "8bit", "precision": "8-bit", "validation": { "schema_version": 1, "repository": "PocketAiHub/Qwen3.8-9B-MLX", "lineage": "regular", "source_repository": "empero-ai/Qwen3.8-9B", "source_revision": "0934f3d2327ff2df2197495278c4c46ae5a56bd9", "base_model": "Qwen/Qwen3.5-9B", "runtime": { "mlx": "0.32.0", "mlx_vlm": "0.6.8" }, "format": { "precision": "8-bit", "language_quantization": { "mode": "affine", "bits": 8, "group_size": 64 }, "vision_tower": "BF16", "native_mtp_included": false, "shard_count": 2, "source_manifest": "workspace/exports/mlx/pocketai-qwen3.8-9b-mlx-8bit/artifact-manifest.json", "source_manifest_sha256": "9b222fd73ae36c659386c917b88ffb71156bbf536cdc2510ff3f337e0decada7" }, "evidence": { "smoke": { "report": "workspace/runs/qwen3.8-9b-regular-benchmarks/8bit/runtime-smoke.json", "report_sha256": "dd8f19678da0e3e838ec145a8e50f7c4294c264bde65230557c08371a4624ee3", "result": { "passed": true, "text_passed": true, "vision_passed": true, "peak_mlx_memory_gb": 12.008154335 } }, "performance": { "report": "workspace/runs/qwen3.8-9b-regular-benchmarks/8bit-4k/report.json", "report_sha256": "1c318f2df60b0e17d9dd37ad8dc8bc2656a4281a7ee511bd08e3242b2838c973", "result": { "passed": true, "formatted_tokens": 4096, "expected": "COBALT-7319", "prefill_tokens_per_second": 3144.796838197671, "decode_tokens_per_second": 57.86438000615739, "peak_mlx_bytes": 11373601846, "kv_bits": null } } }, "release_status": "experimental-community-family-release", "variant_path": "8bit" } }, { "name": "bf16", "path": "bf16", "precision": "BF16", "validation": { "schema_version": 1, "repository": "PocketAiHub/Qwen3.8-9B-MLX", "lineage": "regular", "source_repository": "empero-ai/Qwen3.8-9B", "source_revision": "0934f3d2327ff2df2197495278c4c46ae5a56bd9", "base_model": "Qwen/Qwen3.5-9B", "runtime": { "mlx": "0.32.0", "mlx_vlm": "0.6.8" }, "format": { "precision": "BF16", "language_quantization": null, "vision_tower": "BF16", "native_mtp_included": false, "shard_count": 4, "source_manifest": "workspace/exports/mlx/pocketai-qwen3.8-9b-mlx-bf16/artifact-manifest.json", "source_manifest_sha256": "a12e71156cc58795fea0174b921e1f9fa116b47d70b8fdcc0fde66746dbefefc" }, "evidence": { "performance": { "report": "workspace/runs/qwen3.8-9b-regular-benchmarks/bf16-4k/report.json", "report_sha256": "c35f6bad3957937c3b0e862a746430a3e0def190ce835b37fe4a52a35551e7d0", "result": { "passed": true, "formatted_tokens": 4096, "expected": "COBALT-7319", "prefill_tokens_per_second": 3103.4212658264164, "decode_tokens_per_second": 30.564023533293803, "peak_mlx_bytes": 19848487990, "kv_bits": null } }, "feature": { "report": "workspace/runs/qwen3.8-9b-release/regular-bf16-feature-4k.json", "report_sha256": "ab8032915ca436f06338ab3fd96095c83aa1fe369a1afac0f1f95e822d2f0a66", "result": { "quality": { "passed": true, "pass_count": 12, "case_count": 12 }, "tool_calling": { "passed": true, "pass_count": 8, "case_count": 8 }, "temporal_video": { "passed": true, "expected": "red->blue", "actual": "red->blue" }, "long_context": { "passed": true, "formatted_tokens": 4105, "expected": "COBALT-7319", "actual": "COBALT-7319", "peak_memory_gb": 20.807304778 } } } }, "release_status": "experimental-community-family-release", "variant_path": "bf16" } } ] }