First Look: Benchmarks: Intel Mac mini scores a mixed bag

Last Tuesday, Apple unveiled the newest member of its product line to receive an Intel brain transplant: the Mac mini.

With a choice between a 1.66GHz Intel Core Duo or 1.5GHz Core Solo processor, these new minis replace the current models built with either a 1.42GHz or 1.25GHz PowerPC G4 processor. Macworld Lab has put these two models to the test, and the results—including an updated version of our Speedmark benchmarking suite—are something of a mixed bag.

Like all of the new Intel-based Macs, these Mac minis perform admirably when running applications that have been updated to run on both Intel and PowerPC processors. Cinema 4D results, for example, show the Core Duo Mac mini rendering the test scene in one-third of the time it took the previous high-end mini.

Tasks performed using these Universal Binary applications make up the bulk of the new benchmark results, but as Speedmark is designed to compare how one Mac ranks among the rest of Apple’s lineup in typical day-to-day operation, the current benchmark also includes a few tests using Microsoft’s Office suite, which has not yet been updated.

These non-native applications require Rosetta, OS X’s built-in code translation technology, to run on Intel Macs. Unfortunately, there is a hefty performance penalty associated with this translation. With that in mind, it’s easy to understand why the Intel minis outperformed their PowerPC counterparts in Speedmark, but not by the margin suggested in Apple’s Mac mini marketing materials.

With two processing cores, the 1.66GHz Core Duo Mac mini performed much better than the single processor minis on Universal application tasks that take advantage of multiple processors, like Cinema 4D, iMovie, and iTunes. It even helped close the gap on Rosetta tests such as with the Photoshop suite. The Core Solo, the first Intel-based Mac with just one processing core, had a hard time keeping up with its core duo sibling, but did perform better than the previous low-end mini system in many of the native applications.

One change to the Mac mini’s architecture appears even more controversial than the processor swap: The switch from ATI’s Radeon 9200 graphics card with dedicated memory to integrated Intel graphics that use 64MB of system memory have some users up in arms. And while the debate continues, Macworld’s initial results show the new minis lagging behind their predecessors in Unreal Tournament 2004 by a couple of frames per second.

mac mini lab tests

Speedmark 4.5 Adobe Photoshop CS2 Cinema 4D XL 9.5.21 iMovie 6.0.1 iTunes 6.0.3 Unreal Tournament 2004 Zip Archive
Suite Suite Render Aged filter MP3 Encode Average frame rate 1GB Folder
Mac mini 1.66GHz Core Duo 144 3:03 1:26 1:15 1:40 12.2 3:23
Mac mini 1.5GHz Core Solo 123 4:23 2:57 2:05 2:43 10.4 3:39
Mac mini 1.42GHz G4 113 1:47 4:28 2:02 2:16 14.5 4:13
Mac mini 1.25GHz G4 100 2:01 5:06 2:12 2:32 13.9 4:32
Macbook Pro 1.83GHz Core Duo 152 2:49 1:19 1:16 1:31 48.4 3:54
iMac 1.83GHz Core Duo, 17-inch 202 2:44 1:18 1:08 1:22 50.2 2:45
>Better <Better <Better <Better <Better >Better <Better

Best results in red. Reference systems in italics .

How We Tested : Speedmark 4.5 scores are relative to those of a 1.25GHz Mac mini, which is assigned a score of 100. Adobe Photoshop, Cinema 4D XL, iMovie, iTunes, and Zip Archive scores are in minutes:seconds. All systems were running Mac OS X 10.4.5 with 1GB of RAM, with processor performance set to Highest in the Energy Saver preference pane when applicable. The Photoshop Suite test is a set of 14 scripted tasks using a 50MB file. Photoshop’s memory was set to 70 percent and History was set to Minimum. In iMovie, we applied the Aged video effect to a 1-minute movie. We converted 45 minutes of AAC audio files to MP3 using iTunes’ High Quality setting. We used Unreal Tournament 2004’s Antalus Botmatch average-frames-per-second score; we tested at a resolution of 1,024 by 768 pixels at the Maximum setting with both audio and graphics enabled. We created a Zip archive in the Finder from a 1GB folder.—Macworld Lab testing by James Galbraith and Jerry Jung

Some quick tests with minimum settings show that the both the Intel and PowerPC minis can achieve faster frame rates, but (at least with UT 2004) the PowerPC maintains its lead.

A separate quick test with Nanosaur from Pangea software, tested with the Good settings at 16-bit, 1024-by-768 resolution, show the Intel Macs with an edge. Here’s something to note: The Intel minis didn’t suffer much of a hit at higher settings in Nanosaur, but the higher settings weren’t even available on the PowerPC minis, as those buttons were grayed out.

Check Macworld.com for a complete review and more graphics tests on these systems in the days to come.

[ Jim Galbraith is Macworld ’s lab director. ]

Subscribe to the Apple @ Work Newsletter

Comments