NVIDIA's upcoming mainstream GeForce RTX 4060 Ti & RTX 4060 graphics cards have reportedly been tested according to the latest leaker on the block, @QbitLeaks.
NVIDIA's GeForce RTX 4060 Ti & RTX 4060 "Rumored" Specifications & Performance Revealed, Could Offer Faster Performance Than RTX 3080
The NVIDIA GeForce RTX 4060 Ti and RTX 4060 will be aimed at the sweet spot pricing between $300-$500 US. Both of these graphics cards are expected to launch on the latest Ada Lovelace graphics architecture. Now the leaks come from an entirely new leaker whose credibility is not known at the moment but I guess we all start somewhere. So let's take a look at the specs that @QbitLeaks or FCL has to share with us. Do keep in mind that these are all rumors so take them with a grain of salt.
Well it seems 4060 and 4060 Ti have been tested
4060 Ti: TSE ~8600, avg clock 26XX, power draw ~270-280W.
4060: TSE ~6000, avg clock 27XX, power draw ~230-240W.
— FCL (@QbitLeaks) August 26, 2022
NVIDIA GeForce RTX 4060 Ti "AD104" Graphics Card
The NVIDIA GeForce RTX 4060 Ti is said to utilize the AD104-180-A1 GPU core with 6144 FP32 cores or 48 SMs. That's 20% fewer SM units compared to the full chip which offers 60 SMs or 7680 cores in total. The graphics card is said to feature 10 GB of GDDR6 memory across a 160-bit bus interface and is expected to clock in at 17.5 Gbps for a total of 350 GB/s bandwidth. The card is rumored to have a TBP of around 270-280W and the GPU core is expected to run at an average clock speed of around 2600 MHz.
NVIDIA GeForce RTX 4060 "AD106" Graphics Card
The non-Ti model of the graphics card, the NVIDIA GeForce RTX 4060, is expected to utilize the AD106 GPU core with 3968 FP32 cores or 31 SMs on the AD106-300 die. That's 14% fewer SMs compared to the full 36 SM die or 4608 FP32 cores. The graphics card is expected to rock 8 GB GDDR6 memory across a 128-bit bus interface, running at 17 Gbps for 272 GB/s of bandwidth. NVIDIA's RTX 4060 could also feature an average clock speed as high as 2700 MHz with a TBP between 230-240W.
NVIDIA GeForce RTX 40 Series Graphics Card Lineup (Rumored):
| Graphics Card | GPU | PCB Variant | SM Units / Cores | Memory / Bus | Memory Clock / Bandwidth | TBP | Power Connectors | Launch |
|---|---|---|---|---|---|---|---|---|
| NVIDIA Titan A / GeForce RTX 40? | AD102-450? | PG137-SKU0 | 142/ 18176? | 48 GB / 384-bit | 24 Gbps / 1.15 TB/s | ~800W | 2x 16-pin | TBD |
| NVIDIA GeForce RTX 4090 Ti | AD102-350? | TBD | 144 / 18432? | 24 GB / 384-bit | 24 Gbps / 1.15 TB/s | ~600W | 1x 16-pin | TBD |
| NVIDIA GeForce RTX 4090 | AD102-300? | PG137/139 SKU330 | 128 / 16384? | 24 GB / 384-bit | 21 Gbps / 1.00 TB/s | ~450W | 1x 16-pin | Q4 2022 |
| NVIDIA GeForce RTX 4080 | AD103-300? | PG136/139-SKU360 | 76 / 9728? | 16 GB / 256-bit | 21 Gbps / 672 GB/s | ~420W | 1x 16-pin | Q4 2022 |
| NVIDIA GeForce RTX 4070 | AD104-400? | PG141-SKU331 | 60 / 7680 | 12 GB / 192-bit | 21 Gbps / 504 GB/s | ~300W | 1x 16-pin | Q4 2022 |
| NVIDIA GeForce RTX 4060 | AD106-***? | TBD | >36 / 4608? | 8 GB / 128-bit | TBD | ~200W | 1 x 16-pin | Q1 2023 |
Based on the specifications alone, while the core count gets a 26% and 11% increase, respectively, the memory capacity seems to have changed significantly versus the previous models. The RTX 4060 Ti gets 2 GB more capacity but with lower bandwidth and a cut-down bus interface (160 vs 256-bit) while the RTX 4060 gets a 4 GB memory reduction and cuts down the memory bus even further with lower bandwidth.
The TBP also sees a big increase with the NVIDIA GeForce RTX 4060 Ti rumored to be 70-80 Watt higher than its predecessor and the RTX 4060 is 40W higher than its predecessor. If true, the RTX 4060 will consume more power than an RTX 3070 (220W). Previously, Kopite7kimi did share that NVIDIA's RTX 4060 would consume more power than an RTX 3070.
I don't care about the real release date. I'm just curious about the performance of RTX 4060, which consumes more power than RTX 3070.
— kopite7kimi (@kopite7kimi) June 5, 2022
Based on the specifications, we can extrapolate what the FP32 Compute figures might look like as shown in the table below:
FP32 Compute Horsepower Comparisons (Higher is Better)
Once again, these are all just rumors but the leaker also shared "alleged" performance numbers in 3DMark Time Spy Extreme which can be seen below:
3DMark Time Spy Extreme Graphics
Based on these figures, the NVIDIA GeForce RTX 4060 Ti & RTX 4060 would end up around 45-50% faster than their predecessors, the RTX 3060 Ti and RTX 3060. But this is only a synthetic result and gaming performance could be lower. So more realistically, if this result is anywhere close to reality, we can see a gaming performance improvement in the range of 25-40%. That's about right since the previous gen RTX 3060 series also got an average speed up ranging between 15-25% at max.
NVIDIA is expected to talk about its next-generation gaming GPU architecture at GTC 2022 next month so we will probably get to hear about new cards but the mainstream lineup is usually reserved for later (CES 2023).
The post NVIDIA GeForce RTX 4060 Ti & RTX 4060 Rumored To Feature Over 2.5 GHz Clocks, Top Model Faster Than An RTX 3080 10 GB by Hassan Mujtaba appeared first on Wccftech.