测试机型M4 pro GPU 16核 内存64G 32B-Q4 (内存消耗25G左右)比较9.11和9.8这两个数的大小 total duration: 2m46.371041458s load duration: 21.553083ms prompt eval count: 22 token(s) prompt eval duration: 4.543s prompt eval rate: 4.84 tokens/s eval count: 1325 token(s) eval duration: 2m...
测试机型M4 pro GPU 16核 内存64G 32B-Q4 (内存消耗25G左右)比较9.11和9.8这两个数的大小 total duration: 2m46.371041458s load duration: 21.553083ms prompt eval count: 22 token(s) prompt eval duration: 4.543s prompt eval rate: 4.84 tokens/s eval count: 1325 token(s) eval duration: 2m...
测试机型M4 pro GPU 16核 内存64G 32B-Q4 (内存消耗25G左右)比较9.11和9.8这两个数的大小 total duration: 2m46.371041458s load duration: 21.553083ms prompt eval count: 22 token(s) prompt eval duration: 4.543s prompt eval rate: 4.84 tokens/s eval count: 1325 token(s) eval duration: 2m...