| build: 4898 (8a827f88) with Apple clang version 16.0.0 (clang-1600.0.26.6) for arm64-apple-darwin24.3.0 | |
| 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_M.gguf (version GGUF V3 (latest)) | |
| llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. | |
| Final result: 32.9333 +/- 1.7172 | |
| Random chance: 25.0000 +/- 1.5822 | |
| llama_perf_context_print: load time = 277.24 ms | |
| llama_perf_context_print: prompt eval time = 264353.78 ms / 69469 tokens ( 3.81 ms per token, 262.79 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 = 267232.82 ms / 69470 tokens | |