AX-Unlimited-OCR-3B-MoE-MLX-MXFP8 / release /candidate_performance.json
AutomatosX's picture
Publish verified OCR-aware MXFP8 checkpoint
6708e4d verified
Raw
History Blame Contribute Delete
2.26 kB
{
"model_path": "AX-Unlimited-OCR-3B-MoE-MLX-MXFP8",
"served_revision": null,
"image_path": "test_invoice.png",
"prompt": "<image>document parsing.",
"max_tokens": 256,
"system": {
"platform": "macOS-26.5.2-arm64-arm-64bit-Mach-O",
"processor": "arm",
"python_version": "3.14.6",
"machine": "arm64",
"mlx_version": "0.32.0",
"mlx_vlm_version": "0.6.6",
"chip": "Apple M3 Max",
"total_memory_gb": 128.0
},
"model_load_time_seconds": 0.9827843750099419,
"memory_after_load_mb": 4043.265625,
"num_warmup": 1,
"num_runs": 3,
"mean_tps": 35.14004923388335,
"std_tps": 0.8627581629341593,
"mean_elapsed_seconds": 8.941998055335716,
"mean_peak_memory_mb": 5184.062959,
"runs": [
{
"run": 1,
"elapsed_seconds": 8.715698832995258,
"tokens_generated": 256,
"tokens_generated_source": "mlx-vlm token count",
"tokens_per_second": 36.34797807809006,
"tokens_per_second_source": "mlx-vlm generation_tps",
"peak_memory_mb": 5183.887319,
"memory_delta_mb": 1337.1867550000002,
"process_peak_rss_mb": 4058.71875,
"prompt_tokens": 697,
"prompt_tokens_per_second": 422.9274407258055,
"finish_reason": "length"
},
{
"run": 2,
"elapsed_seconds": 9.117345000006026,
"tokens_generated": 256,
"tokens_generated_source": "mlx-vlm token count",
"tokens_per_second": 34.685109648852176,
"tokens_per_second_source": "mlx-vlm generation_tps",
"peak_memory_mb": 5184.1507790000005,
"memory_delta_mb": 1337.1880710000005,
"process_peak_rss_mb": 4065.359375,
"prompt_tokens": 697,
"prompt_tokens_per_second": 413.1939079712154,
"finish_reason": "length"
},
{
"run": 3,
"elapsed_seconds": 8.992950333005865,
"tokens_generated": 256,
"tokens_generated_source": "mlx-vlm token count",
"tokens_per_second": 34.38705997470784,
"tokens_per_second_source": "mlx-vlm generation_tps",
"peak_memory_mb": 5184.1507790000005,
"memory_delta_mb": 1337.1880710000005,
"process_peak_rss_mb": 4065.5625,
"prompt_tokens": 697,
"prompt_tokens_per_second": 463.0680271067021,
"finish_reason": "length"
}
]
}