模型與效能

{
  "method": {
    "kind": "llama-server-completion",
    "prompt_sha256": "d1073ca91137cbd8b8c777e44e3634b6d02a3f492eaf4805ec47f5f68c9654fb",
    "server_sha256": "4bc6b545e77fc15471493503fe2d63a3e7dfee0a46e6735b2244c8f4eb934bf5",
    "llama_cpp_revision": "5aeac37a35b44fde4bdffaec9159f2fcb253b622",
    "app_commit": "5cadd45b7a78e2c6abec380dcc2f6a89d31d3b66",
    "app_dirty": true,
    "generation_tokens_requested": 128,
    "repetitions": 3,
    "cache": "prompt cache disabled; model warm after one unmeasured 16-token request",
    "rss_sampling_interval_ms": 100,
    "synthetic_input": true
  },
  "parameters": [
    {
      "backend": "cpu",
      "model_id": "qwen3-1.7b",
      "context_size": 2048,
      "threads": 2,
      "batch_size": 128,
      "ubatch_size": 128,
      "generated_tokens": 128,
      "quantization": "Q4_K_M"
    },
    {
      "backend": "metal",
      "model_id": "qwen3-1.7b",
      "context_size": 2048,
      "threads": 2,
      "batch_size": 128,
      "ubatch_size": 128,
      "generated_tokens": 128,
      "quantization": "Q4_K_M"
    }
  ],
  "limitations": [
    "Single machine; not a prediction for other M-series chips.",
    "Generation speed is not transcription accuracy or meeting-summary quality.",
    "RSS is a sampled process-resident-memory peak, not total unified/GPU allocation.",
    "Power draw and thermal throttling were not measured.",
    "128 output tokens are forced for comparability; this is a short synthetic benchmark."
  ]
}