NVIDIA recently quietly launched a new budget graphics card that neatly slots itself between the GTX 1050 and the GTX 1050 Ti. The new GTX 1050 3GB, as the name suggests, features 3GB of GDDR5 memory. The new card is closer to the GTX 1050 Ti than the name would suggest, however as it uses the same 768 CUDA cores instead of the 640 of the GTX 1050 2GB. The GDDR5 memory is where the card differs from the GTX 1050 Ti though as NVIDIA has cut the number of memory controllers by one along with the corresponding ROPs and cache meaning that the new GTX 1050 3GB has a smaller memory bus and less memory bandwidth than both the GTX 1050 2GB and GTX 1050 Ti 4GB.
Specifically, the GTX 1050 with 3GB GDDR5 has a 96-bit memory bus that when paired with 7 Gbps GDDR5 results in maximum memory bandwidth of 84 GB/s versus the other previously released cards' 128-bit memory buses and 112 GB/s of bandwidth.
Clockspeeds on the new GTX 1050 3GB start are a good bit higher than the other cards though with the base clocks starting at 1392 MHz which is the boost clock of the 1050 Ti and running up to 1518 MHz boost clockspeeds. Thanks to the clockspeeds bumps, the theoretical GPU performance of 2.33 TFLOPS is actually higher than the GTX 1050 Ti (2.14 TFLOPS) and existing GTX 1050 2GB (1.86 TFLOPS) though the reduced memory bus (and loss of a small amount of ROPs and cache) will hold the card back from surpassing the Ti variant in most workloads – NVIDIA needs to maintain product segmentation somehow!
| NVIDIA GTX 1050 2GB | NVIDIA GTX 1050 3GB | NVIDIA GTX 1050 Ti 4GB | AMD RX 560 4GB | |
|---|---|---|---|---|
| GPU | GP107 | GP107 | GP107 | Polaris 11 |
| GPU Cores | 640 | 768 | 768 | 896 or 1024 |
| Texture Units | 40 | 48 | 48 | 64 |
| ROPs | 32 | ? | 32 | 16 |
| GPU Base | 1354 | 1392 | 1290 | 1175 |
| GPU Boost | 1455 | 1518 | 1392 | 1275 |
| TFLOPS | 1.86 | 2.33 | 2.14 | up to 2.6 |
| Memory | 2GB GDDR5 | 3GB GDDR5 | 4GB GDDR5 | 2GB or 4GB GDDR5 |
| Memory Clockspeed | 7 Gbps | 7 Gbps | 7 Gbps | 7 Gbps |
| Memory Bus | 128-bit | 96-bit | 128-bit | 128-bit |
| Memory Bandwidth | 112 GB/s | 84 GB/s | 112 GB/s | 112 GB/s |
| TDP | 75W | 75W | 75W | 60W to 80W |
| Pricing | ~$150 | ~$160 (Estimate) | ~$200 | ~$160 |
The chart above compares the specifications of the GTX 1050 3GB with the GTX 1050 and the GTX 1050 Ti on the NVIDIA side and the AMD RX 560 which appears to be its direct competitor based on pricing. The new 3GB GTX 1050 should compete well with AMD's Polaris 11 based GPU as well as NVIDIA's own cards in the budget gaming space where hopefully the downside of a reduced memory bus will at least dissuade cryptocurrency miners from adopting this card as an entry level miner for Ethereum and other alt coins giving gamers a chance to buy something a bit better than the GTX 1050 and RX 550 level at close to MSRP while the miners fight over the Ti and higher variants with more memory and compute units.
NVIDIA did not release formal pricing or release date information, but the cards are expected to launch in June and prices should be around $160 to $180 depending on retailer and extra things like fancier coolers and factory overclocks.
What are your thoughts on the GTX 1050 3GB? Is it the bastion of hope budget gamers have been waiting for? hehe Looking around online it seems pricing for these budget cards has somewhat returned to sane levels and hopefully alternative options like these aimed at gamers will help further stabilize the market for us DIYers that want to game more than mine. I do wish that NVIDIA could have changed the name a bit to better differentiate the card, maybe the GTX 1050G or something but oh well. I suppose so long as the 640 CUDA core GTX 1050 doesn't ever get 3GB GDDR5 at least gamers will be able to tell them apart by the amount of memory listed on the box or website.
Also read:
This doesn’t exactly scream
This doesn’t exactly scream of offering customers clear choices and being transparent, is there even a single spec that’s the same as the 1050 2GB? Trying to pretend the only difference is the RAM could be seen as being highly deceptive.
Sure a more distinctive
Sure a more distinctive naming would have been better but there’s the 3GB to recognize it and it have more core, higher frequency, more texture unit to balance the narrower memory bus (and less ROP probably) at least it’s not like the AMD RX560 which has the exact same name (and some AIB didn’t even report core number) and reduced number of core without something to balance
Indeed and i wasn’t singling
Indeed and i wasn’t singling out just this card or just Nvidia as like you say AMD are just as guilty, however it’s very hypocritical to say you scrapped a program intended to provide customers with clear choices and then do something like this.
Basically don’t do things like this while acting like butter wouldn’t melt and you’re an innocent victim because you were only trying to be transparent.
I don’t get the crypto
I don’t get the crypto comment.
They could easily check if the card is in 1x or 4x PCI-E mode and disable all but a tiny fraction of GPU/RAM.
They don’t do that because they don’t want to.
they should have called this
they should have called this the 1050 boost, or the 1050TIse model,something other than just plain ole 1050, or even the 1055?
While it is another budget model, this confusing naming scheme is complete shyte. I mean, at least Nvidia didn’t do that with any other model…
oh wait, they did with the 1030 and 1060.
I guess by Nvidia’s definition that as long as one can dig and dig and dig and search and dig some more to finally find the specs of a card, then that is transparent enough and no need to change the graphics or logos on the box.
Man Nvidia is down to its
Man Nvidia is down to its Bargain Bin Binning trying to make use of every die that comes off of TSMC’s diffusion lines. So Nvidia wants to make the most of those not so good dies that may not have as many memory channels working or ROPs, and ROPs really matter so that’s still not Known(?) about.
Pascal is going to be around a good long time what with AMD not really wanting to be in the Flagship GPU business again just yet. AMD’s targeting the mainstream GPUs where the real money is made and AMD’s going to get more Vega on the market via the integrated Graphics on Raven Ridge and Intel’s EMIB/MCM Kaby Lake G. So look for Nvidia to only be targeting the mainstream for its next generation also so that 1080Ti is going to remain Pascal the longest with only the GTX 1180/1170 in line for the latest Nvidia GPU micro-arch for gaming GPUs.
Nvidia is in its binning mode now that the coin mining demand means that Nvidia can begin scaling back the Pascal GP104, GP106 and GP108 based production lines! Now GP102 is used for Quadro in addition to the GP102 binned dies going to the GTX 1080Ti. So that GP102 is going to remaing in production for any GP102 related Professional products with longer product support lifecycles than the consumer SKUs receive and Nvidia will still want any GP102 binnned dies able to be sold as GTX 1080TIs for a good while longer.
TSMC? The GTX 1050 and 1050
TSMC? The GTX 1050 and 1050 Ti are made at Samsung foundry…
Well whatever diffusion line
Well whatever diffusion line of any fab that Nvidia has a contract with, and that binning process is across all of Nvidia’s offerings. You will see the GTX 1080Ti offered for purchase the longest anyways because it’s based on a binned GP102 die! And because that GP102 die was mostly designed to be used for Nvidia’s Quadro offerings then GP102 dies will be in production well after and GP104, GP106 and GP108 die production is history.
Nvidia’s Quadro offerings will be on the market longer as that professional market demands that there be an assured supply of replacement Pascal/Quadro offerings and I’ll wager that the GTX 1180 will not outperform the GTX 1080Ti if Nvidia does not give the GTX 1180 more than 64 ROPs. Nvidia will still want to be offering the GTX 1080Ti just to have a market for those GP102 dies that can not make the grade to become Quadro Branded and Nvidia will want to get more life out of Pascal what with AMD not currently interested in the Flagship GPU contest.
AMD’s not going to want to offer up any Flagship GPU competition until there are enough Vega 20 binned dies that do not make the grade to become Radeon Pro WX Branded and then AMD may just have some motivation to make use of any Binned Vega 20 dies in some consumer Flagship GPU variants if AMD’s Vega 20 die based Radeon Pro WX Variants needs are being supplied and there still is a surplus of binned dies remaining.
Nvidia’s Flagship Gaming GTX 1080Ti GPU is completely the result of the binned GP102 dies that Nvidia could not offer for its high margin Quadro offerings so AMD will at some time have a supply on Vega 20 dies that are just not able to make the grade to be Radeon Pro WX! Let’s hope that maybe AMD will offer some Dual Vega 20 die based offerings also for the Professional AI markets as that would mean that there could be some possible Dual Vega 20 die Connsumer offerings also for some Flagship GPUs as an afterthought Flagship Gaming GPUs from AMD.
The more AMD sells Vega 20 die based Professional GPUs the more Binned Vega 20 dies there will be as the result of the fabrication die/wafer yield process. So There is hope that AMD will have some binned dies to maybe cobble together a binned Vega 20 die based Gaming Flagship offering in has happened in the past it can still happen with Vega.
Navi is going to be made of modular/scalable GPU dies like Epyc/Threadripper is for CPUs and then AMD will be able to create an entire lineup of Navi variants at the same time from low end to flagship no waiting months/years required.