NVIDIA GeForce RTX 3090 Ti confirmed to feature Micron’s 21 Gbps GDDR6X memory

Published: Nov 29th 2021, 08:03 GMT   Comments

NVIDIA GeForce RTX 3090 Ti gets Micron GDDR6X memory

Ultra-fast memory for NVIDIA’s upcoming flagship.

The GeForce RTX 3090 Ti is to feature 21 Gbps memory from Micron. The Taiwanese media outlet “Uniko’s Hardware”, which often shares information on unreleased products has now provided the exact code from Micron’s GDDR6X memory catalog. According to this information, a memory codenamed “MT61K512M32KPA-21U” is to be used for RTX 3090 Ti. The code appears to confirm it will be a 21 Gbps bandwidth per module.

Apart from the speed, the card is also the first product to utilize 16Gb (2GB) modules based on GDDR6X technology. NVIDIA has thus far been unable to provide this 2GB GDDR6X memory variant to any of its products because such modules simply did not exist. This led the company to use GDDR6 memory on its workstation products that require high-capacity frame buffers and as many as 24 modules on its current flagship, the RTX 3090 non-Ti.

With the upcoming Ti model, NVIDIA will be able to limit the number of modules to 12, this should simplify the design of the card by not requiring an actively cooled backplate (the RTX 3090 has half of the modules located on the backside). However, the requirement of active back cooling may still prevail because the card will be a true power hog. According to the rumors, the RTX 3090 Ti is to have a default TDP of 450W, over 100W more than the non-Ti model.

NVIDIA RTX 3090 Ti is the first GeForce card to feature full GA102 GPU with 10752 CUDA cores. Thanks to the faster memory and 384-bit wide memory bus, the card will be able to cross 1 TB/s of bandwidth for the time in GeForce history.

The card is now expected to launch in January, following the launch of RTX 3080 12GB and RTX 3070 Ti 16GB.

NVIDIA GeForce RTX 30 Specifications
VideoCardzRTX 3090 TiRTX 3090RTX 3080 TiRTX 3080
Picture[ to be leaked ]
GPUGA102-350GA102-300GA102-225GA102-200
GPU Clusters
 
84
 
82
 
80
 
68
CUDAs
 
10752
 
10496
 
10240
 
8704
RT Cores
 
84
 
82
 
80
 
68
Tensors/TMUs
 
336
 
328
 
320
 
272
Base ClockTBC
 
1395 MHz
 
1365 MHz
 
1440 MHz
Boost ClockTBC
 
1695 MHz
 
1665 MHz
 
1710 MHz
Memory
 
24 GB G6X
 
24 GB G6X
 
12 GB G6X
 
10 GB G6X
Bus
 
384-bit
 
384-bit
 
384-bit
 
320-bit
Memory Clock
 
21 Gbps
 
19.5 Gbps
 
19 Gbps
 
19 Gbps
Bandwidth
 
1008 GB/s
 
936 GB/s
 
912 GB/s
 
760 GB/s
TDP
 
450W
 
350W
 
350W
 
320W
MSRPTBC
 
$1,499
 
$1,199
 
$699
Release DateJanuary 2022September 24th, 2020June 3rd, 2021September 17th, 2020



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