NVIDIA introduces GeForce RTX 4070 Ti graphics card at $799

Published: Jan 3rd 2023, 15:30 GMT   Comments

NVIDIA RTX 4070 Ti is finally official

Today NVIDIA introduced its third and thus far the cheapest RTX 40 desktop GPU.

NVIDIA RTX 4070 Ti specs and price, Source: NVIDIA

The RTX 4070 Ti is a high-end GPU to offer up to 40 TFLOPs of compute performance. This card is based on AD104 GPU with 7680 CUDA cores, which is a full configuration of this graphics processor. The card is equipped with 12GB of GDDR6X memory clocked at 21 Gbps. Since the GPU is attached to a 192-bit memory bus, the maximum bandwidth will be limited to 504 GB/s, which is actually 104 GB/s slower than its predecessor, the RTX 3070 Ti.

NVIDIA 4070 Ti is to launch as a partner card only, which means no Founder Edition, although the render above may suggest otherwise. Almost every RTX 4070 Ti card that has been leaked or unveiled so far has three fans and 2 to 3.5-slot cooling design. This should be more than enough for the 285W TDP, though.

NVIDIA RTX 4070 Ti custom cards, Source: NVIDIA

This is a third desktop card based on Ada Lovelace architecture and third Ada GPU to be announced, following AD102 (RTX 4090) and AD103 (RTX 4080). They are all based on the same process TSMC 4N custom process node. The AD104 GPU will have around 10B transistors fewer than AD103 (35.8B in total), with the die size around 295 mm².

Reviewers are to publish their test results as early as tomorrow, while the card is to become available for sale on January 5th. The MSRP of $799 will apply to the cheapest models at launch, mainly the cards that do not offer factory-overclocking.

NVIDIA GeForce RTX 40 Series Specs
VideoCardz.comGeForce RTX 4090GeForce RTX 4080GeForce RTX 4070 Ti
Picture
Board-SKUPG136-SKU330PG136-SKU360PG141-SKU331
ArchitectureAda (TSMC 4N)Ada (TSMC 4N)Ada (TSMC 4N)
GPUAD102-300AD103-300AD104-400
GPU Transistors
 
76.3B
 
45.9B
 
35.8B
GPU Die Size
 
608 mm²
 
379 mm²
 
295 mm²
SMs
 
128
 
76
 
60
CUDA Cores
 
16384
 
9728
 
7680
Boost Clock
 
2.5 GHz
 
2.5 GHz
 
2.6 GHz
FP32 Compute
 
81.9 TFLOPS
 
48.6 TFLOPS
 
38.4 TFLOPS
Memory
 
24 GB G6X
 
16 GB G6X
 
12 GB G6X
Memory Bus
 
384-bit
 
256-bit
 
192-bit
Memory Speed
 
21 Gbps
 
22.4 Gbps
 
21 Gbps
Bandwidth
 
1008 GB/s
 
736 GB/s
 
504 GB/s
Default TGP
 
450W
 
320W
 
285W
MSRP
 
1599 USD
 
1199 USD
 
799 USD
Release DateOctober 12th, 2022November 16h, 2022January 5th, 2023



Comment Policy
  1. Comments must be written in English and should not exceed 1000 characters.
  2. Comments deemed to be spam or solely promotional in nature will be deleted. Including a link to relevant content is permitted, but comments should be relevant to the post topic. Discussions about politics are not allowed on this website.
  3. Comments and usernames containing language or concepts that could be deemed offensive will be deleted.
  4. Comments complaining about the post subject or its source will be removed.
  5. A failure to comply with these rules will result in a warning and, in extreme cases, a ban. In addition, please note that comments that attack or harass an individual directly will result in a ban without warning.
  6. VideoCardz has never been sponsored by AMD, Intel, or NVIDIA. Users claiming otherwise will be banned.
  7. VideoCardz Moderating Team reserves the right to edit or delete any comments submitted to the site without notice.
  8. If you have any questions about the commenting policy, please let us know through the Contact Page.
Hide Comment Policy
Comments