build: 4998 (d41f0150) 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 31 key-value pairs and 339 tensors from ./DeepSeek-R1-Distill-Qwen-7B-Q3_K_L.gguf (version GGUF V3 (latest))

Final result: 31.4985 +/- 2.5727
Random chance: 28.6842 +/- 2.5050


llama_perf_context_print:        load time =     246.39 ms
llama_perf_context_print: prompt eval time =   78846.76 ms / 17768 tokens (    4.44 ms per token,   225.35 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 =   79962.49 ms / 17769 tokens
ggml_metal_free: deallocating