Got a tip for us?
Let us know
Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
First Geekbench for base M3
- Thread starter APCX
- Start date
- Sort by reaction score
You know current Intel and AMD CPUs currently run above 5Ghz and boost about 6Ghz.
Pretty much all of it. I mean, it’s a trivial arithmetics exercise.
Yet, achieving that within the same power constraint is quite impressive
Not necessarily. They said that it’s twice as fast as the M1 in certain tasks. The M2 and M3 have hardware decoders for ProRes video that the base M1 lacks, so in video related tasks the jump in performance will be greater. In others the jump might be less than double.
Double the performance for what? I don’t think they meant double the single core or multi core performance.
From their 2x claim:
- Testing conducted by Apple in September and October 2023 using preproduction 24-inch iMac systems with Apple M3, 8-core CPU, 10-core GPU, 24GB of RAM, and 2TB SSD, as well as production 24-inch iMac systems with Apple M1, 8-core CPU, 8-core GPU, 16GB of RAM, and 2TB SSD. Adobe Premiere Pro (Beta) 24.1 tested with Scene Edit Detection using a 2-minute and 19-second project with Apple ProRes 422 HQ media, at 1920x1080 resolution and 23.98 frames per second. Performance tests are conducted using specific computer systems and reflect the approximate performance of iMac.
I’m placing a bet right now.
14” MBP with M3 has a different body, as the missing USB-C port puts the HDMI and SDXC card slot closer together.
I would NOT be surprised if that model only has 1 fan.
If it doesn’t, it will be because Apple used current design and spent no R&D on changing it.
But I wouldn’t be surprised if it has 1 fan.
Just like 24” iMac tiers.
It seems so.
I’m sure that one is enough. I can’t recall ever hearing the fans from my M1 mini or M1 Pro MacbookPro.It seems so.
No, I did not. Honestly, I don’t pay as much attention to computer news as I used to. However, this is 4GHz in the base model, which is still a pretty big deal. I’m sure that 5 and 6GHz Intel and AMD chips aren’t going into entry/midrange laptops or slimline all-in-ones (if they’re even going into laptops at all, they might be limited to workstation computers that have beefy power supplies for all I know).
Lower cost of running because of lower power needs, lower system heat, those are some benefits of more efficient processors for devices on mains power.
Oh wow I totally missed that, and it makes total sense with their strategy in recent years
Yeah sombody else shared that a moment ago as well, I totally missed that but am not surprised at all with what we've seen in recent years.It seems so.
1 fan is probably 100% sufficient for M1, M2, and M3. I can't imagine an extra fan would even provide benefit given that the one fan only runs a very small amount of the time to quickly cool down the chip. On laptop that is. Desktop always runs but it's also cooling all ports, power supply, everything. Laptops are more spread out and Mac mini.
WOW! so they Goa boost the frequency to a 4GHZ just to squeeze 20 percent more power than the M2.
What a JOKE.
We were all told 3nm was going to be revolutionary and a big performance increase.
Totally over hyped.
What a JOKE.
We were all told 3nm was going to be revolutionary and a big performance increase.
Totally over hyped.
I guess it is probably the targeted performance for the added P-cores. The M3 Max to be there or thereabout with the top desktop offer from Intel and AMD as it is still a consumer product and to compete within it with a 2,199$ Mac Studio instead of specialized offer as the very expensive Ultra (Threadripper territory).
Of course it would be stunning coming from a chip that runs on battery power without a hiccup!
Score for Gfxbench at 52.2fps is disappointing. Not sure what is going on with Gfxbench lately, but some scores show the A16 or A15 being faster than the A17 which is weird!
gfxbench.com
GFXBench - Unified cross-platform 3D graphics benchmark database
The first unified cross-platform 3D graphics benchmark database for comparing Android, iOS, Windows 8, Windows Phone 8 and Windows RT capable devices based on graphics processing power.
A node shrink doesn’t improve performance on its own. It just allows you to run the CPU at a higher frequency for the same power consumption. That’s exactly what we’re seeing here. So, what’s the problem?