build: 5600 (d17a809e) 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 M4 Max) - 49151 MiB free
llama_model_loader: loaded meta data with 43 key-value pairs and 363 tensors from ./Dolphin-Mistral-24B-Venice-Edition-Q3_K_M.gguf (version GGUF V3 (latest))

Final result: 69.3333 +/- 1.6849
Random chance: 25.0083 +/- 1.5824


llama_perf_context_print:        load time =    4667.65 ms
llama_perf_context_print: prompt eval time =  189292.95 ms / 36666 tokens (    5.16 ms per token,   193.70 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 =  190208.90 ms / 36667 tokens
ggml_metal_free: deallocating
ggml_metal_mem_pool_free: freeing memory pool, num heaps = 0 (total = 0)
ggml_metal_mem_pool_free: freeing memory pool, num heaps = 0 (total = 0)
ggml_metal_mem_pool_free: freeing memory pool, num heaps = 0 (total = 0)
ggml_metal_mem_pool_free: freeing memory pool, num heaps = 0 (total = 0)
ggml_metal_mem_pool_free: freeing memory pool, num heaps = 0 (total = 0)
ggml_metal_mem_pool_free: freeing memory pool, num heaps = 0 (total = 0)
ggml_metal_mem_pool_free: freeing memory pool, num heaps = 0 (total = 0)
ggml_metal_mem_pool_free: freeing memory pool, num heaps = 0 (total = 0)