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-IQ3_S.gguf (version GGUF V3 (latest))

Final result: 46.7202 +/- 1.8267
Random chance: 25.0251 +/- 1.5859


llama_perf_context_print:        load time =    1478.40 ms
llama_perf_context_print: prompt eval time = 3003478.13 ms / 36519 tokens (   82.24 ms per token,    12.16 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 = 3005310.10 ms / 36520 tokens
ggml_metal_free: deallocating