| build: 5150 (2db9ba14) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0 | |
| llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free | |
| llama_model_loader: loaded meta data with 40 key-value pairs and 292 tensors from ./Watt-Tool-8B-Q4_K_M.gguf (version GGUF V3 (latest)) | |
| Final Winogrande score(750 tasks): 74.0000 +/- 1.6027 | |
| llama_perf_context_print: load time = 297.22 ms | |
| llama_perf_context_print: prompt eval time = 75766.44 ms / 22192 tokens ( 3.41 ms per token, 292.90 tokens per second) | |
| llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second) | |
| llama_perf_context_print: total time = 76251.82 ms / 22193 tokens | |
| ggml_metal_free: deallocating | |