{ "cases": [ { "coherence_detail": "coherent surface form", "coherent": true, "elapsed_seconds": 0.2227, "fact_detail": "privacy/locality concepts present", "facts_correct": true, "fixture": null, "generation_tokens": 26, "id": "text_privacy", "passed": true, "peak_memory_gb": 2.744799434, "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 reduces the need for cloud storage and transmission of sensitive clinical data, thereby enhancing privacy." }, { "coherence_detail": "coherent surface form", "coherent": true, "elapsed_seconds": 0.0383, "fact_detail": "all expected facts present", "facts_correct": true, "fixture": null, "generation_tokens": 2, "id": "text_fact_extraction", "passed": true, "peak_memory_gb": 2.776603786, "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": 0.989, "fact_detail": "all expected facts present", "facts_correct": true, "fixture": "synthetic_clinical_document.png", "generation_tokens": 32, "id": "image_clinical_document", "passed": true, "peak_memory_gb": 5.36413155, "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": 0.73, "fact_detail": "all expected facts present", "facts_correct": true, "fixture": "synthetic_clinic_chart.png", "generation_tokens": 5, "id": "image_chart", "passed": true, "peak_memory_gb": 5.36413155, "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": 0.8184, "mlx_vlm_revision": "dd79a5d8caf3edafd6fa9e6326d7ce4977ddcbfc", "model_path": "OpenMed/North-Micro-Vision-Instruct-6bit-mlx", "passed": true, "runtime_versions": { "huggingface-hub": "1.27.0", "mlx": "0.32.0", "mlx-lm": "0.31.3", "mlx-metal": "0.32.0", "mlx-vlm": "0.6.10", "transformers": "5.15.0" }, "schema_version": 1, "source_model": "CohereLabs/North-Micro-Vision-Instruct", "source_revision": "373bda96ac70bf89f99f7048f420cf00dc07c149", "variant": "6bit", "weights": { "actual": { "sha256": "564282d38108f0406bed6602fde32bc3f3877b3848f42cf0ad3d514aba9ced02", "size": 2658753473 }, "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": 100663296, "shape": [ 262144, 384 ], "size": 100663296 } } }, "payload_valid": true, "reference": { "sha256": "21f16dea6c6274241538410c6c017155f2b5b223f8d31e2e05d687679fdcd2a0", "size": 2658753473 }, "reference_hash_match": false, "reference_size_match": true } }