build: 5120 (e8a62631) 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 31 key-value pairs and 339 tensors from ./DeepSeek-R1-Distill-Qwen-7B-Q3_K_M.gguf (version GGUF V3 (latest))

Final result: 29.8667 +/- 1.6723
Random chance: 25.0000 +/- 1.5822


llama_perf_context_print:        load time =     244.09 ms
llama_perf_context_print: prompt eval time =  208162.58 ms / 68469 tokens (    3.04 ms per token,   328.92 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 =  209829.13 ms / 68470 tokens
ggml_metal_free: deallocating