Discussion Intel Meteor, Arrow, Lunar & Panther Lakes + WCL Discussion Threads

[Tigerick]

Wildcat Lake (WCL) Specs

Intel Wildcat Lake (WCL) is upcoming mobile SoC replacing Raptor Lake-U. WCL consists of 2 tiles: compute tile and PCD tile. It is true single die consists of CPU, GPU and NPU that is fabbed by 18-A process. Last time I checked, PCD tile is fabbed by TSMC N6 process. They are connected through UCIe, not D2D; a first from Intel. Expecting launching in Q1 2026.

		Intel Raptor Lake U	Intel Wildcat Lake 15W?	Intel Lunar Lake		Intel Panther Lake 4+0+4
Launch Date		Q1-2024	Q2-2026	Q3-2024		Q1-2026
Model		Intel 150U	Intel Core 7	Core Ultra 7 268V		Core Ultra 7 365
Dies		2	2	2		3
Node		Intel 7 + ?	Intel 18-A + TSMC N6	TSMC N3B + N6		Intel 18-A + Intel 3 + TSMC N6
CPU		2 P-core + 8 E-cores	2 P-core + 4 LP E-cores	4 P-core + 4 LP E-cores		4 P-core + 4 LP E-cores
Threads		12	6	8		8
Max Clock		5.4 GHz	?	5 GHz		4.8 GHz
L3 Cache		12 MB		12 MB		12 MB
TDP		15 - 55 W	15 W ?	17 - 37 W		25 - 55 W
Memory		128-bit LPDDR5-5200	64-bit LPDDR5	128-bit LPDDR5x-8533		128-bit LPDDR5x-7467
Size		96 GB		32 GB		128 GB
Bandwidth				136 GB/s
GPU		Intel Graphics	Intel Graphics	Arc 140V		Intel Graphics
RT		No	No	YES		YES
EU / Xe		96 EU	2 Xe	8 Xe		4 Xe
Max Clock		1.3 GHz	?	2 GHz		2.5 GHz
NPU		GNA 3.0	18 TOPS	48 TOPS		49 TOPS

As Hot Chips 34 starting this week, Intel will unveil technical information of upcoming Meteor Lake (MTL) and Arrow Lake (ARL), new generation platform after Raptor Lake. Both MTL and ARL represent new direction which Intel will move to multiple chiplets and combine as one SoC platform.

MTL also represents new compute tile that based on Intel 4 process which is based on EUV lithography, a first from Intel. Intel expects to ship MTL mobile SoC in 2023.

ARL will come after MTL so Intel should be shipping it in 2024, that is what Intel roadmap is telling us. ARL compute tile will be manufactured by Intel 20A process, a first from Intel to use GAA transistors called RibbonFET.

 

[adroc_thurston]

skt scr ≠ IPC.

yes it's much harder than that.

skt scr ≠ IPC. AMD pj +10-15% IPC fr Zen 5, 10% fr Zen 6. 2 yr old trufe bmb dawg.

you're getting low teens and you're liking it.
The question is always fmax big dawg.

 

[madtronik]

Not my point.
RMB was the last time AMD iterated mobile uncore.

RMB was really some great stuff for laptop. And what did AMD get out of it? They were as rare as hen's teeth in available laptops at the time. I've seen later many more chinese minipcs with that CPU than laptops. Heck, most of Zen 4 laptop processors that I've ever seen have been mostly chinese minipcs. OEMs voted with their design wins.

Intel really needs to re-think if they ever want to turn a profit again. They have ceded most of the high profit markets to AMD with their current strategy.

I would agree; however, which one makes the most profit? Intel seems to be ignoring DC which I see as a much bigger crime (from a profit standpoint).

They are not ignoring anything. RIght now they don't have any way to compete in the short term. AMD created chiplets just to be able to compete with Intel in DC. Without chiplets, the fab advantage already gave the win to Intel without doing anything.

Lisa really needs to re-think it if she wants AMD to capture 40% of client market. It is not going to happen if AMD releases new products only every 2.5 years.

iPhone is only 20% of the global smartphone market. Do you think that gives Tim Cook any trouble to sleep at night? Nokia arrived at 40% market share just at the time when it was entering smartphone oblivion by selling clamshells to Africa. Gaining market share just for the sake of it is the most stupid business decision a CEO can make. Proper CEOs chase $$$, not market share.

I for me I am very happy with Panther Lake, we can have some terrific laptops with that chip and it gives a lifeline to Intel. Having 2 companies competing and selling x86 makes ARM's position very difficult. I am an x86 fanboy.

 

[adroc_thurston]

RMB was really some great stuff for laptop. And what did AMD get out of it? They were as rare as hen's teeth in available laptops at the time. I've seen later many more chinese minipcs with that CPU than laptops. Heck, most of Zen 4 laptop processors that I've ever seen have been mostly chinese minipcs. OEMs voted with their design wins.

Not the point I'm making.
They haven't updated mobile uncore since RMB.

 

[madtronik]

Not the point I'm making.
They haven't updated mobile uncore since RMB.

Well, the point I was trying to make wasn't that RMB was great, just that they did pour quite a bit of resources in the mobile designs and they just got nothing out of it. So, it is logical that they stopped funding that when they just have many other opportunities than can provide ample returns. Just as with Radeon. If you create some quite competitive consumer GPUs and the market just keeps buying NVIDIA at a higher price with lower performance, why bother?

 

[adroc_thurston]

So, it is logical that they stopped funding that when they just have many other opportunities than can provide ample returns

They didn't.
AMD SoC people are just lazy schmucks when it comes to client parts.

 

[OneEng2]

They are not ignoring anything. RIght now they don't have any way to compete in the short term. AMD created chiplets just to be able to compete with Intel in DC. Without chiplets, the fab advantage already gave the win to Intel without doing anything.

I think (my speculation) is that creating chiplets/tiles is quite easy. Creating an architecture that scales well with the # of chiplets, can handle the memory requirements in a scalable way, and minimizes the performance losses in the architecture due to the chiplet/tile interfaces is the entire ball game, not just a cute trick.

Arguably, TSMC has held the process advantage since 7nm.... and therefore so has AMD. In fact, I would argue that Intel's historic reliance on maintaining FAB dominance over the entire rest of the world has been their downfall.

"Server First" architecture approach makes sense from a profit standpoint. It's great if this approach also gives you an edge in client .... but not necessary. I think Intel spent many years drunk off of the DC profit as well as the package deals with their CPU's (which they still enjoy in many OEM deals today I suspect).

I know that many are thinking that NVL will not compete well with Zen 6; however, I am not so sure. I am pretty sure that in DC, it isn't even going to be close .... and from a profit standpoint?

 

[Hulk]

AMD will get ~10-12%, not 12-14%.

As I said if Intel can pull another 6 to 8% out of Cougar Cove for Coyote Cove AMD will need to match, which would require 12 to 14%.

I didn't make any prediction as to what will happen. I'm extrapolating where Intel and AMD will need to be in order stay "IPC competitive" for the next gen. desktop P cores.

If what we are seeing from Cougar Cove is valid Intel has put down the first card on the table. Yes, it's not tremendous but it's not a "flat" Redwood Cove "sidegrade" either.

 

[Joe NYC]

iPhone is only 20% of the global smartphone market. Do you think that gives Tim Cook any trouble to sleep at night? Nokia arrived at 40% market share just at the time when it was entering smartphone oblivion by selling clamshells to Africa. Gaining market share just for the sake of it is the most stupid business decision a CEO can make. Proper CEOs chase $$$, not market share.

That's the thing. It seems like AMD has ambition to capture the mainstream to Premium part of the market, without putting in the work to earn that market.

Intel is putting in the work, correcting past mistakes and stumbles, especially with Panther Lake.

So even if AMD has a good CPU in Medusa, it will not be facing a hapless design like Meteor Lake, it will face Panther Lake that corrected most of the problems with Meteor Lake.

I for me I am very happy with Panther Lake, we can have some terrific laptops with that chip and it gives a lifeline to Intel. Having 2 companies competing and selling x86 makes ARM's position very difficult. I am an x86 fanboy.

Qualcomm + NVidia, both will be trying with WoA

 

[adroc_thurston]

So even if AMD has a good CPU in Medusa, it will not be facing a hapless design like Meteor Lake, it will face Panther Lake that corrected most of the problems with Meteor Lake.

PTL has a joke CPU for the 2026 product cycle.
Get real.

 

[Hulk]

I wonder how well the performance overall will be for Intel vs AMD though? If Intel has issues clocking the design up (and retaining yields), then AMD's performance will likely eclipse Intel in the next gen lineup.

It is even worse if you look at the margins that are made at higher binning vs lower binning. Again, I worry more about Intel's ability to make money than them producing chips that have higher IPC than AMD's next gen design (which I expect is a very distinct possibility based on the data currently available).

If Intel is already hitting 5.1GHz for Cougar Lake and 3.8 for Darkmont does that mean it looks good or bad for ramping up clocks for Nova Lake?

On one hand they could be hitting 5.1 easily. But on the otherhand, the silicon that does 5.1 might be rare, and only a 1 or 2 cores might hit that frequency in the ones that do make the cut?

Just curious if we can discern from the Panther Lake release regarding 18A yields and frequency? Because the process still is the big unknown for Intel at this point. Yes, they seem to have got it out the door but how is it doing when it comes to looking into the future. ie is there a giant garbage can full of wafers!?

 

[Khato]

ie is there a giant garbage can full of wafers!?

It's a pretty small garbage can, wafers don't take up that much space

Unfortunately there aren't going to be any meaningful indicators on 18A health to be gleaned from PTL laptop availability. eg, there are going to be way more PTL laptops available than Strix Halo, but that doesn't mean PTL yields are better than Strix Halo. Just have to be content with the knowledge that yields aren't great, but they aren't bad either. Being in a state where yield can no longer be doubled is at least decent.

It still is unfortunate that 18A didn't meet the PDK and hence frequency is limited to 5.1 GHz. But thanks to lack of x86 competition that's still enough to stay on top in the mobile space.

We'll have to wait and see how N2P does with NVL.

 

[fastandfurious6]

OK pantherlake CPU numbers are out



tldr Panther is DOA.... cheapest model has similar price with HALO 392.

- as expected, intel cinebench cores inside©™
- inflated bench numbers, terrible perf in real world
- Blender and 7zip- 100% slower to prevgens 7945HX and 285HX, 40-70% to HALO 392
- Geekbench 6 is obviously cooked...


The practical part is market and pricing.
Pantherlake laptops cost 1500-2500 bucks, no dgpu, 1.2kg
cinebench cores and barely rtx4050 perf

with the same 1500 bucks you can get AMD HALO 392, 1.2kg
12 full zen5 cores plus fat iGPU with RTX5060 performance

other AMD options at same price,
- HX370/470 + dgpu RTX 5060, 2kg
- 7945HX 16 full zen4 cores + RTX 5060 but 2.5kg

but cheap Halo eclipses both. if available.


Ultimately, pantherlake replaces nothing. It's eaten by Halo 392 for breakfast at same price point or even apple silicon... M5 PRO will smoke PTL in games too

 

[Hulk]

OK pantherlake CPU numbers are out

View attachment 137526

tldr Panther is DOA.... cheapest model has similar price with HALO 392.

- as expected, intel cinebench cores inside©™
- inflated bench numbers, terrible perf in real world
- Blender and 7zip- 100% slower to prevgens 7945HX and 285HX, 40-70% to HALO 392
- Geekbench 6 is obviously cooked...


The practical part is market and pricing.
Pantherlake laptops cost 1500-2500 bucks, no dgpu, 1.2kg
cinebench cores and barely rtx4050 perf

with the same 1500 bucks you can get AMD HALO 392, 1.2kg
12 full zen5 cores plus fat iGPU with RTX5060 performance

other AMD options at same price,
- HX370/470 + dgpu RTX 5060, 2kg
- 7945HX 16 full zen4 cores + RTX 5060 but 2.5kg

but cheap Halo eclipses both. if available.


Ultimately, pantherlake replaces nothing. It's eaten by Halo 392 for breakfast at same price point or even apple silicon... M5 PRO will smoke PTL in games too

How does Ryzen AI Max Pro 390 score almost 25,000 for CB R23? Is it 4P + 8C cores like the HX370? My HX370 will only do around 4.1/3.1 or so for the Big/Little Zen 5 cores. Just wondering if the 390 is fundamentally different or it's just higher frequency?

 

[DavidC1]

This is also true for the macOS and Linux kernel they get larger with more features being added. Difference is Microsoft doesn’t give a crap about Windows optimisation now.

Apple had to overhaul its M5 GPU architecture to match the B390 at similar wattage in Cyberpunk. The GPU in the M4 is much weaker despite it being on N3E.

It does, but not unobtainable levels like on CPU, because CPU's ST performance is still the #1 prize, which doesn't come except from the creativity and brilliance from the engineers, which is separate from Moore's Law. The similar comparison is if common computer usage was all Cinebench like.

Shrink would have been the minimum. Lack of LP cores a big gap for AMD in mobile.

It isn't just LP cores though. AMD has no experience in getting battery life to ARM levels, while Intel did back when they were trying to penetrate the market back 15 years ago. And they didn't even succeed right away. It took them 2 iterations to do that. The second one, Moorestown failed at that, and lost LG design win. First was not worth talking about of course. They finally succeeded with Medfield. ARM battery life = 15-16 hours web browsing battery life with FHD display using a 50WHr battery, 2.5W screen-on idle.

Remembrandt made no progress in that regard. They had a good core for load, but not for actual battery life. Intel gave up on the battery life department after the Atoms and only came back with Lunarlake. I had Atom Windows Tablet. It idled at 1.3W with the 7-inch screen on. AMD hasn't and still doesn't have anything comparable. One reason I assume is because AMD were just content with taking Intel's marketshare, while Intel was already at the limit and had to try taking ARM marketshare to make more money. Now AMD is only focused on AI share.

It will be hard for AMD to gain share in mobile in H2 2026 with a stale line up.

The marketshare projections doesn't pan out to what the company wants. It only happens if they actually make things what the market wants. In other words, it's just talk.

It makes perfect sense why gaming mobile PTL would be 2+8+4. Lighting up 4 P cores to get more performance than 2 + 2 e cores would blow the power budget enough to leave nothing for the rest of the chip in a 15-20 watt envelope. Any game that absolutely requires more than 2 P cores at above E core performance to perform well is either not going to work well with an iGPU or can't do well in a handheld power budget to begin with. Pushing 30 watts to make it make any sense raises your build cost for a larger battery and beefier cooling and gets beat by Strix Halo.

Pantherlake already prioritizes using the E cores for gaming though.

 

[DavidC1]

RMB was really some great stuff for laptop. And what did AMD get out of it? They were as rare as hen's teeth in available laptops at the time. I've seen later many more chinese minipcs with that CPU than laptops. Heck, most of Zen 4 laptop processors that I've ever seen have been mostly chinese minipcs. OEMs voted with their design wins.

You can't take meaningful share with one generation. Marketshare is related to trust. Zen 2 was just one generation away from Zen, and most mindshare was still at Intel. Doing ok one gen and coasting is what's called a "one hit wonder" and everyone forgets about you. Consistency is key.

Well, the point I was trying to make wasn't that RMB was great, just that they did pour quite a bit of resources in the mobile designs and they just got nothing out of it. So, it is logical that they stopped funding that when they just have many other opportunities than can provide ample returns. Just as with Radeon. If you create some quite competitive consumer GPUs and the market just keeps buying NVIDIA at a higher price with lower performance, why bother?

This is same with Radeon. Consumers don't care about computers. Those that know the difference between i9 mobile and i9 desktops are ostracized and considered nerds, the people that are seen as weird and deserve to be alone forever. That's the commoner thinking.

All they know is #1, which has been Nvidia practically forever. So the problem is AMD's lack of GPUs that compete with 4090s 5090s. The mid-range efficiency strategy plainly doesn't work. They gotta aim for 600-700mm2, x90 performance every generation, and do it for 4-5 years at least.

The difference between #1 and #2 athletes are one having too much money and attention, and the other having barely above average worker salaries.

@Hulk brief search says your Strix Point is P+C while Strix Halo is all P.

 

[Geddagod]

OK pantherlake CPU numbers are out

View attachment 137526

tldr Panther is DOA.... cheapest model has similar price with HALO 392.

- as expected, intel cinebench cores inside©™
- inflated bench numbers, terrible perf in real world
- Blender and 7zip- 100% slower to prevgens 7945HX and 285HX, 40-70% to HALO 392
- Geekbench 6 is obviously cooked...


The practical part is market and pricing.
Pantherlake laptops cost 1500-2500 bucks, no dgpu, 1.2kg
cinebench cores and barely rtx4050 perf

with the same 1500 bucks you can get AMD HALO 392, 1.2kg
12 full zen5 cores plus fat iGPU with RTX5060 performance

other AMD options at same price,
- HX370/470 + dgpu RTX 5060, 2kg
- 7945HX 16 full zen4 cores + RTX 5060 but 2.5kg

but cheap Halo eclipses both. if available.


Ultimately, pantherlake replaces nothing. It's eaten by Halo 392 for breakfast at same price point or even apple silicon... M5 PRO will smoke PTL in games too

 

[Geddagod]

It's Q3'28 A14 parts for whole 3 vendors.
Your opinion has no relation to product roadmaps.

If only your opinion had any relation to Zen 5 performance lmao.

N2 is right on schedule.

Q4 2025 HVM for what products launching soon and not in the 2H of 2026?

Overlapped no product schedules.

Cuz they missed Apple's launch schedule. Atp they should have stopped lying about it entering HVM so early then.

 

[adroc_thurston]

If only your opinion had any relation to Zen 5 performance lmao.

Yeah, it won server so hard Intel DCAI is a past tense thingy.

Q4 2025 HVM for what products launching soon and not in the 2H of 2026?

Nothing overlapped N2 HVM, everything's going to N2p pmuch.

Cuz they missed Apple's launch schedule

Missed AMD and QCOM too.
Happens.
A14 is the same for all three doe.

 

[OneEng2]

If Intel is already hitting 5.1GHz for Cougar Lake and 3.8 for Darkmont does that mean it looks good or bad for ramping up clocks for Nova Lake?

On one hand they could be hitting 5.1 easily. But on the otherhand, the silicon that does 5.1 might be rare, and only a 1 or 2 cores might hit that frequency in the ones that do make the cut?

Just curious if we can discern from the Panther Lake release regarding 18A yields and frequency? Because the process still is the big unknown for Intel at this point. Yes, they seem to have got it out the door but how is it doing when it comes to looking into the future. ie is there a giant garbage can full of wafers!?

It seems like the pricing of PTL laptops puts it into a pretty exclusive club. I wonder if this is because of the cost of 18A and yields. You wouldn't think Intel would have wanted PTL to be this expensive of a platform?

It still is unfortunate that 18A didn't meet the PDK and hence frequency is limited to 5.1 GHz. But thanks to lack of x86 competition that's still enough to stay on top in the mobile space.

We'll have to wait and see how N2P does with NVL.

I think Intel does LOTS of things right for OEM mobile. Things they have been refining for decades where AMD is still quite new at the game. Things not necessarily directly related to just the CPU.

Your comment about N2 is also right on the money. While I am having doubts about 18A clock scaling and yields, N2 with NVL might indeed be a winner. I just keep thinking that ARL is so bottlenecked by the ring bus latency issues that a few tweaks and N2P might just free the architecture up a great deal ..... but we will see.

OK pantherlake CPU numbers are out

View attachment 137526

tldr Panther is DOA.... cheapest model has similar price with HALO 392.

- as expected, intel cinebench cores inside©™
- inflated bench numbers, terrible perf in real world
- Blender and 7zip- 100% slower to prevgens 7945HX and 285HX, 40-70% to HALO 392
- Geekbench 6 is obviously cooked...


The practical part is market and pricing.
Pantherlake laptops cost 1500-2500 bucks, no dgpu, 1.2kg
cinebench cores and barely rtx4050 perf

with the same 1500 bucks you can get AMD HALO 392, 1.2kg
12 full zen5 cores plus fat iGPU with RTX5060 performance

other AMD options at same price,
- HX370/470 + dgpu RTX 5060, 2kg
- 7945HX 16 full zen4 cores + RTX 5060 but 2.5kg

but cheap Halo eclipses both. if available.


Ultimately, pantherlake replaces nothing. It's eaten by Halo 392 for breakfast at same price point or even apple silicon... M5 PRO will smoke PTL in games too

Halo makes nearly that clock speed 2 full shrinks behind PTL. That is worrisome IMO. I mean, I know we have been stalled a bit with clock increases, but still.

 

[DavidC1]

4 Xe version nearly comparable in games to Lunarlake 140V:

The complete list of Intel Panther Lake laptops (Core Ultra X9 388H, Core Ultra 9 386H, Core Ultra 7 365)

28W 386H vs 30W 258V
Far Cry 6: 48 vs 52 fps
Horizon Forbidden West: 46 vs 45 fps
Shadow of Tomb Raider: 62 vs 66 fps
The Witcher 3: 74 vs 78 fps

 

[MoistOintment]

It seems like the pricing of PTL laptops puts it into a pretty exclusive club. I wonder if this is because of the cost of 18A and yields. You wouldn't think Intel would have wanted PTL to be this expensive of a platform?

Haven't new CPU launches in mobile debuted in more expensive "flagship" laptops for a while now? I imagine between tight initial supply during ramp + increase RAM prices where these higher end laptops can absorb the price hike a little better, it'll be a while before lower PTL laptops start trickling out

 

[511]

If Intel is already hitting 5.1GHz for Cougar Lake and 3.8 for Darkmont does that mean it looks good or bad for ramping up clocks for Nova Lake?

On one hand they could be hitting 5.1 easily. But on the otherhand, the silicon that does 5.1 might be rare, and only a 1 or 2 cores might hit that frequency in the ones that do make the cut?

Top Bins unlikely to be in volume for a while

Just curious if we can discern from the Panther Lake release regarding 18A yields and frequency? Because the process still is the big unknown for Intel at this point. Yes, they seem to have got it out the door but how is it doing when it comes to looking into the future. ie is there a giant garbage can full of wafers!?

It's not possible if we take a look at Intel 4 vs Intel 3 cause despite being the same node for the most part Intel 3 clocks higher and decent bit better perf/watt for the same stuff due to other improvement 18A gives me similar feeling to Intel 4 in terms of where it is at in terms of process need bit more work to mature.

4 Xe version nearly comparable in games to Lunarlake 140V:

The complete list of Intel Panther Lake laptops (Core Ultra X9 388H, Core Ultra 9 386H, Core Ultra 7 365)

28W 386H vs 30W 258V
Far Cry 6: 48 vs 52 fps
Horizon Forbidden West: 46 vs 45 fps
Shadow of Tomb Raider: 62 vs 66 fps
The Witcher 3: 74 vs 78 fps

If you look at it 3X compute for 12Xe3 vs 4Xe3 and we get 2X gains feels like memory bandwidth bound for 12Xe3

 

[DavidC1]

Pantherlake and Gorgon Point Lenovo is nearly identical in price:

https://www.lenovo.com/gb/en/configurator/cto/index.html?bundleId=83RWCTO1WWGB1

https://www.lenovo.com/gb/en/configurator/cto/index.html?bundleId=83Q6CTO1WWGB1

$36 price difference.

If you look at it 3X compute for 12Xe3 vs 4Xe3 and we get 2X gains feels like memory bandwidth bound for 12Xe3

Not necessarily. The frames are high enough where CPU starts to have an effect, and it's essentially the same CPU. It's 1/3 cut but in Pixel Backend and Geometry it's only cut by half. Other unknown fixed function is likely cut less than 1/3rd too. Fixed function is like the time it takes you to get ready versus the travelling time. You may be able to speed up the travelling time, but you will be limited by time it takes to get ready. This is why GPUs like 5090 starts needing 4K resolutions to be worth the older parts.

Even if a system is not bound, to get 100% gains still requires the "not bound" part increasing by 100%, because application variety is wide and some will be more and some less than others. Getting 1.3x gains from 2x bandwidth is not "bound" either.

The Expertbook is faster in some games than Zenbook Duo despite having LPDDR5-8533 and only X7 358H.

https://www.notebookcheck.net/Asus-ExpertBook-Ultra-review-One-helluva-debut-for-Intel-Panther-Lake-X7.1209366.0.html

As a laptop, 16 hour WiFi from 1800p OLED and 70Whr battery is also quite good. It's beating the 1080p Ryzen 350 with same WHr by 2 hours.

 

[DavidC1]

Wildcat Lake is looking real good now. I bet you another reason not scaling so well is that the 12 Xe core is more power bound, and he's running on rather low settings and Pantherlake has room. So at higher settings there might be a bigger difference. It's good to see the 4 Xe version is not much of a compromise if any.

At 12 hours it's high enough for me where I can accept a battery capacity sacrifice for a lighter device. I think Toshiba can pull off a FHD IPS display 2-in-1 with 2.2lbs weight and 45-50WHr battery. It probably can do 16 hours with that. The weight and size would really make it a viable tablet/laptop hybrid.

 

[Fjodor2001]

PTL has higher IPC than Zen5/5c:

https://wccftech.com/intel-panther-lake-powered-by-the-new-cougar-cove-p-cores-and-darkmont-e-cores-takes-a-lead-over-amd/