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-Q3_K_S.gguf (version GGUF V3 (latest))

Final result: 51.4667 +/- 1.8262
Random chance: 25.0083 +/- 1.5824


llama_perf_context_print:        load time =    1572.52 ms
llama_perf_context_print: prompt eval time =  123381.08 ms / 36600 tokens (    3.37 ms per token,   296.64 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 =  124278.85 ms / 36601 tokens
ggml_metal_free: deallocating