{
  "conversion_transformers": "5.16.1",
  "source_model": "ProCreations/grug-27b-v2-candidate-20260912-qwen",
  "source_revision": "79a2b2b81bf6ee0123da02467cf187db04e03708",
  "llama_cpp_commit": "2a3005c23f60cb38dab70b8ea2ddbd969bcf3e87",
  "mtp_embedded_in_every_text_gguf": true,
  "artifacts": [
    {
      "file": "grug-27b-v2-Q4_K_M.gguf",
      "bytes": 16998721440,
      "sha256": "5db0549d718c0accbe5979af0a959099f7165e3b0bea7a8604c7a1bd6872363f",
      "mtp_tensor_count": 15,
      "mtp_matrix_quantization": "Q8_0",
      "smoke_stdout": "| model                          |       size |     params | backend    | threads |            test |                  t/s |\n| ------------------------------ | ---------: | ---------: | ---------- | ------: | --------------: | -------------------: |\n| qwen35 27B Q4_K - Medium       |  15.82 GiB |    27.32 B | CPU        |      24 |            pp16 |         21.50 ± 0.00 |\n| qwen35 27B Q4_K - Medium       |  15.82 GiB |    27.32 B | CPU        |      24 |             tg8 |          3.16 ± 0.00 |\n\nbuild: 2a3005c (1)\n",
      "smoke_stderr": ""
    },
    {
      "file": "grug-27b-v2-Q5_K_M.gguf",
      "bytes": 19682420640,
      "sha256": "bf02d822be68618f9dca224065aa47e0cbb478de8b432a0ccc672a28d06438f8",
      "mtp_tensor_count": 15,
      "mtp_matrix_quantization": "Q8_0",
      "smoke_stdout": "| model                          |       size |     params | backend    | threads |            test |                  t/s |\n| ------------------------------ | ---------: | ---------: | ---------- | ------: | --------------: | -------------------: |\n| qwen35 27B Q5_K - Medium       |  18.32 GiB |    27.32 B | CPU        |      24 |            pp16 |         13.27 ± 0.00 |\n| qwen35 27B Q5_K - Medium       |  18.32 GiB |    27.32 B | CPU        |      24 |             tg8 |          2.81 ± 0.00 |\n\nbuild: 2a3005c (1)\n",
      "smoke_stderr": ""
    },
    {
      "file": "grug-27b-v2-Q6_K.gguf",
      "bytes": 22533851040,
      "sha256": "c110ad0b8863c06dacd753c41c301ba3d7c4901e5776d0d80e2396b6c184fd0c",
      "mtp_tensor_count": 15,
      "mtp_matrix_quantization": "Q8_0",
      "smoke_stdout": "| model                          |       size |     params | backend    | threads |            test |                  t/s |\n| ------------------------------ | ---------: | ---------: | ---------- | ------: | --------------: | -------------------: |\n| qwen35 27B Q6_K                |  20.98 GiB |    27.32 B | CPU        |      24 |            pp16 |         15.91 ± 0.00 |\n| qwen35 27B Q6_K                |  20.98 GiB |    27.32 B | CPU        |      24 |             tg8 |          2.53 ± 0.00 |\n\nbuild: 2a3005c (1)\n",
      "smoke_stderr": ""
    },
    {
      "file": "grug-27b-v2-Q8_0.gguf",
      "bytes": 29047084960,
      "sha256": "01431cb3864ee4cd7ef5a9e5d73079194f6c3bca66d0cac5ce19502e2e948f44",
      "mtp_tensor_count": 15,
      "mtp_matrix_quantization": "Q8_0",
      "smoke_stdout": "| model                          |       size |     params | backend    | threads |            test |                  t/s |\n| ------------------------------ | ---------: | ---------: | ---------- | ------: | --------------: | -------------------: |\n| qwen35 27B Q8_0                |  27.04 GiB |    27.32 B | CPU        |      24 |            pp16 |         17.03 ± 0.00 |\n| qwen35 27B Q8_0                |  27.04 GiB |    27.32 B | CPU        |      24 |             tg8 |          1.92 ± 0.00 |\n\nbuild: 2a3005c (1)\n",
      "smoke_stderr": ""
    },
    {
      "file": "grug-27b-v2-Q3_K_M.gguf",
      "bytes": 13752764320,
      "sha256": "3b36b201c4c7053bea301533d2804aa41912f701c19e320bffe0cfa5e72e07c4",
      "mtp_tensor_count": 15,
      "mtp_matrix_quantization": "Q8_0",
      "smoke_stdout": "| model                          |       size |     params | backend    | threads |            test |                  t/s |\n| ------------------------------ | ---------: | ---------: | ---------- | ------: | --------------: | -------------------: |\n| qwen35 27B Q3_K - Medium       |  12.80 GiB |    27.32 B | CPU        |      24 |            pp16 |         17.12 ± 0.00 |\n| qwen35 27B Q3_K - Medium       |  12.80 GiB |    27.32 B | CPU        |      24 |             tg8 |          4.01 ± 0.00 |\n\nbuild: 2a3005c (1)\n",
      "smoke_stderr": ""
    },
    {
      "file": "mmproj-grug-27b-v2-F16.gguf",
      "bytes": 927606976,
      "sha256": "1335119dd8d9f9e8c4b0a65de12b7d218cfc47282c706a0c6be0dd85be209da6"
    }
  ],
  "elapsed_seconds": 1267.8098618984222,
  "conversion_time_remaining_validation": "GPU generation and embedded MTP parity must pass before public release",
  "post_conversion_validation": {
    "completed": true,
    "record": "results/runtime_validation.json",
    "basic_functional_checks": "12/12 for every quantization with MTP off and on",
    "native_api_checks": "14/15 for every mode; reasoning alias is unsupported by the pinned llama-server parser",
    "token_parity": "Measured and reported per quantization; not a bit-identical decoding guarantee",
    "coding_grader": "Corrected final-answer replay on HF CPU Jobs; see results/coding_rescore.json"
  }
}