scores/DeepSeek-R1-Distill-Qwen-7B-F16.hsw

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 27 key-value pairs and 339 tensors from ./DeepSeek-R1-Distill-Qwen-7B-F16.gguf (version GGUF V3 (latest))

750	58.66666667%	[55.1070%, 62.1380%]


llama_perf_context_print:        load time =     489.74 ms
llama_perf_context_print: prompt eval time =  378646.50 ms / 126788 tokens (    2.99 ms per token,   334.85 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 =  384487.38 ms / 126789 tokens
ggml_metal_free: deallocating