build: 5170 (658987cf) with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.4.0
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 339 tensors from ./Hammer2.1-7b-Q8_0.gguf (version GGUF V3 (latest))

Final result: 38.9333 +/- 1.7816
Random chance: 25.0000 +/- 1.5822


llama_perf_context_print:        load time =     316.60 ms
llama_perf_context_print: prompt eval time =  197007.43 ms / 67719 tokens (    2.91 ms per token,   343.74 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 =  198698.88 ms / 67720 tokens
ggml_metal_free: deallocating