scores/DeepSeek-R1-Distill-Qwen-7B-iq3_m.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 31 key-value pairs and 339 tensors from ./DeepSeek-R1-Distill-Qwen-7B-IQ3_M.gguf (version GGUF V3 (latest))

750	55.73333333%	[52.1583%, 59.2500%]


llama_perf_context_print:        load time =     249.03 ms
llama_perf_context_print: prompt eval time =  377141.15 ms / 126788 tokens (    2.97 ms per token,   336.18 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 =  382541.56 ms / 126789 tokens
ggml_metal_free: deallocating