| build: 5080 (78a1ba0a) with Apple clang version 16.0.0 (clang-1600.0.26.6) for arm64-apple-darwin24.2.0 | |
| llama_model_load_from_file_impl: using device Metal (Apple M3 Pro) - 27647 MiB free | |
| llama_model_loader: loaded meta data with 33 key-value pairs and 292 tensors from ./DeepSeek-R1-Distill-Llama-8B-IQ3_S.gguf (version GGUF V3 (latest)) | |
| Final Winogrande score(750 tasks): 65.0667 +/- 1.7420 | |
| llama_perf_context_print: load time = 286.58 ms | |
| llama_perf_context_print: prompt eval time = 70525.90 ms / 22192 tokens ( 3.18 ms per token, 314.66 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 = 71010.05 ms / 22193 tokens | |
| ggml_metal_free: deallocating | |