{ "cases": [ { "coherence_detail": "coherent surface form", "coherent": true, "elapsed_seconds": 0.423, "fact_detail": "privacy/locality concepts present", "facts_correct": true, "fixture": null, "generation_tokens": 37, "id": "text_privacy", "passed": true, "peak_memory_gb": 3.23761089, "prompt": "In one concise sentence, explain how running a vision-language model entirely on-device can improve privacy for clinical documents.", "prompt_tokens": 30, "response": "Running a vision-language model entirely on-device can improve privacy for clinical documents by reducing the need to transmit sensitive data over the internet, thus minimizing the risk of data breaches and unauthorized access." }, { "coherence_detail": "coherent surface form", "coherent": true, "elapsed_seconds": 0.0375, "fact_detail": "all expected facts present", "facts_correct": true, "fixture": null, "generation_tokens": 1, "id": "text_fact_extraction", "passed": true, "peak_memory_gb": 3.281032518, "prompt": "A synthetic note states: \"The follow-up appointment is scheduled for Tuesday at 10:30 AM.\" What day is the follow-up? Answer with only the day.", "prompt_tokens": 44, "response": "Tuesday" }, { "coherence_detail": "coherent surface form", "coherent": true, "elapsed_seconds": 1.2672, "fact_detail": "all expected facts present", "facts_correct": true, "fixture": "synthetic_clinical_document.png", "generation_tokens": 31, "id": "image_clinical_document", "passed": true, "peak_memory_gb": 5.843571694, "prompt": "This is synthetic test data. In one concise sentence, report the exact patient name, record ID, medication with dose and frequency, and allergy shown in the image.", "prompt_tokens": 1161, "response": "The synthetic test data includes patient Alex Rivera (Record ID: SYN-2048), prescribed Metformin 500 mg twice daily, with a penicillin allergy." }, { "coherence_detail": "coherent surface form", "coherent": true, "elapsed_seconds": 0.8766, "fact_detail": "all expected facts present", "facts_correct": true, "fixture": "synthetic_clinic_chart.png", "generation_tokens": 4, "id": "image_chart", "passed": true, "peak_memory_gb": 5.843571694, "prompt": "Which category has the tallest bar, and what exact value is printed above it? Answer concisely.", "prompt_tokens": 1053, "response": "Screening, 42" } ], "device": { "architecture": "applegpu_g15d", "device_name": "Apple M3 Ultra", "max_buffer_length": 373662154752, "max_recommended_working_set_size": 498216206336, "memory_size": 549755813888, "resource_limit": 499000 }, "load_seconds": 2.9559, "model_path": "OpenMed/North-Micro-Vision-Instruct-8bit-mlx", "passed": true, "runtime": "openmed.mlx.OpenMedMLXVisionLanguageModel", "runtime_versions": { "huggingface-hub": "1.27.0", "mlx": "0.32.0", "mlx-lm": "0.31.3", "mlx-metal": "0.32.0", "openmed": "1.0.0", "transformers": "5.15.0" }, "schema_version": 1, "source_model": "CohereLabs/North-Micro-Vision-Instruct", "source_revision": "373bda96ac70bf89f99f7048f420cf00dc07c149", "variant": "8bit", "weights": { "actual": { "sha256": "912eb8d8463c14539790711b4516beee01510963b34e1d892ecfaa4838906018", "size": 3145292807 }, "embedding_health": { "healthy": true, "tensors": { "language_model.model.embed_tokens.biases": { "dtype": "mlx.core.bfloat16", "healthy": true, "nonzero_count": 8388608, "shape": [ 262144, 32 ], "size": 8388608 }, "language_model.model.embed_tokens.scales": { "dtype": "mlx.core.bfloat16", "healthy": true, "nonzero_count": 8388608, "shape": [ 262144, 32 ], "size": 8388608 }, "language_model.model.embed_tokens.weight": { "dtype": "mlx.core.uint32", "healthy": true, "nonzero_count": 134217728, "shape": [ 262144, 512 ], "size": 134217728 } } }, "payload_valid": true, "reference": { "sha256": "82c8ba545f0c9e533f8c08cfaa8420d27ca3c460470e236c28164ef9afc025e4", "size": 3145292807 }, "reference_hash_match": false, "reference_size_match": true } }