{
  "model": "Zyphra/ZAYA1-8B",
  "quantization": {
    "method": "compressed-tensors",
    "format": "float-quantized",
    "scheme": "NVFP4",
    "scheme_variant": "w4a4",
    "num_bits_weight": 4,
    "num_bits_activation": 4,
    "type": "float",
    "strategy": "tensor_group",
    "group_size": 16,
    "target_modules": [
      "Linear"
    ],
    "ignore": [
      "lm_head",
      "re:.*router.*",
      "re:.*norm.*",
      "re:.*qkv.*",
      "re:.*cca.*"
    ],
    "weight_packed_dtype": "uint8",
    "weight_scale_dtype": "float8_e4m3fn",
    "weight_global_scale_dtype": "float32",
    "input_global_scale_dtype": "float32",
    "zero_point": "none (symmetric)",
    "compressor": "NVFP4PackedCompressor"
  },
  "calibration": {
    "data_path": "data/calibration/arcmix/calibration_data.pt",
    "num_samples_used": 977,
    "batch_size": 1,
    "linears_calibrated": 936
  },
  "mixed_precision": {
    "threshold": 500.0,
    "outlier_layers": [
      1,
      19,
      31,
      37,
      39,
      65,
      69,
      71,
      73,
      75,
      77,
      79
    ],
    "bf16_exempted_modules": 384,
    "w4a4_compressed_modules": 936,
    "description": "12 MoE layers where max_abs > 500 kept at BF16 (384 Linears). FusedMoE requires uniform quantization per layer."
  },
  "hardware": {
    "gpu": "NVIDIA GeForce RTX 5070 Ti",
    "vram": "16 GB",
    "cuda": "13.0"
  },
  "modules_compressed": 936,
  "output_size_bytes": 9492784787,
  "dry_run": false
}