{
  "base_model": "google/gemma-4-E2B-it",
  "base_revision": "3e22461f65e89153144f8adb70e3b8c2cc9845a7",
  "engine_git": "https://github.com/pytorch/executorch",
  "engine_revision": "ca56e1ffdba1c902d9202021d7297982d3501439",
  "qnn_sdk": "2.37.0.250724",
  "target_soc": "SM8450",
  "hexagon_arch": "v69",
  "context": 2048,
  "quantization": "mixed W4 block32 FFN gate/up/down; all other decoder projections W8 per-channel; final 8 cross-decoder FFN down projections restored to W8; A16; KV16; A16 x W8 attention boundary; Q4 group32 portable embeddings",
  "weight_bits": 4,
  "weight_granularity": "block",
  "block_size": 32,
  "w4_ffn_only": true,
  "w4_ffn_down": true,
  "w8_ffn_down_tail": 8,
  "compiled_shards": 11,
  "qnn_delegate_count": 12,
  "largest_delegate_bytes": 504553728,
  "source_calibration_context": 2048,
  "position_table_audit": true,
  "model_name": "Gemma4-E2B-Dflash2-Android",
  "original_baseline_pte_sha256": "38faf5d2337d9fb2b75b2ddca0fb3c63d916b2795c55bff6a1b6b92c027e8c7b",
  "original_baseline_pte_bytes": 3361616512,
  "original_baseline_pte_name": "gemma4-e2b-v69-mixed4b32-ffn-all-tail8w8-kv16-quality-2k-shard11.pte",
  "dflash2_target": {
    "name": "gemma4-e2b-dflash2-verify-2k.pte",
    "bytes": 3361310336,
    "sha256": "c05fe24cb87fe20f3c2fdf3bb942755486f4c34785ad4d28a5b5546a7378983b",
    "features": [
      3,
      13,
      23,
      33
    ],
    "verification_width": 4,
    "target_weights_changed_for_feature_export": false,
    "context_loading_order": "Head context loaded first; execution order unchanged"
  },
  "vision_target": {
    "name": "gemma4-e2b-dflash2-vision-verify-2k.pte",
    "sha256": "6475a64ba4c82a85dd635bde40cc51ece8effe47366565a1c6e58d48862cdbba",
    "source_sha256": "c05fe24cb87fe20f3c2fdf3bb942755486f4c34785ad4d28a5b5546a7378983b",
    "weights_and_QNN_contexts_unchanged": true,
    "modification": "Portable embedding operator descriptor alias only",
    "device_validated": true
  }
}