Recently WolStame, Lenovo China’s Gaming Desktop Product Planning Manager has shared some information regarding the RTX 4060. This is merely speculation and not an actual leak/rumor. Although, since the source is quite reputable, most of these rumors may end up being true.
RTX 4060, What Do We Know So Far
Due to the RTX 4080 fiasco, the specifications of many GPUs are at risk of being changed. From what we know so far, the RTX 4060 is based on the AD106 GPU. The 4060 Ti may be pushed to AD104 if NVIDIA deems it appropriate. Other than that, we expect 8GB of G6X memory over a 128-bit memory bus. The 4352 FP32 count amounts to roughly 24TFLOPs of compute power (2.8GHz) which is almost 2x the RTX 3060.
WolStame mentions that the RTX 4060 will be 20% faster than the RTX 3060. This is a moderate generation-on-generation uplift making the 4060 equal to the RTX 3070. The power consumption, however, is lower than the 3060 at 150-180W. NVIDIA is pushing more and more for efficiency gains as RDNA3 is a major threat, especially in the budget segment.
The RTX 4060 will come in around $399, or equal to the RTX 3060 Ti‘s MSRP. It appears that team green has made some adjustments to their lineup which make the previously expected price of $499 very less likely. It has also been stated that NVENC along with DLSS 3 have been improved. This is most likely a comparison against Ampere highlighting the inclusion of the AV1 encoder/decoder.
The expected release date is ‘618‘ translating to 6/18/2023 or the 18th of June, 2023. What’s interesting is that WolStame has given us an actual release date instead of a time window.
Despite our initial expectations, the RTX 4060 is being pushed back to June next year. The RTX 4070 Ti and possibly the 4070 will be unveiled at CES 2023. Therefore, the lower end Ada-based RTX 4060 and RTX 4050 are nowhere in sight for the foreseeable future.
|SKU||Chip||FP32/CUDA||SMs||Max Clock||Cache||Memory Bus||VRAM||Memory Spec||Speed (Gbps)||TDP|
|RTX 4000 Titan||AD102-450||18432||144||3.0GHz+?||96MB?||384/382-bit||48GB||GDDR6X||24||~800W|
|RTX 4090 Ti||AD102-350||18176||142||3.0 GHz?||96MB||382-bit||24GB||GDDR6X||24||600W?|
450W+ (TGP) / 660W (Max TGP)
|RTX 4080 Ti||AD102||14848||116||2.7 GHz?||80MB?||320-bit||20GB||GDDR6X||23||420W|
|RTX 4080 (Variant 1)||AD103-300-A1||9728||76||2.505GHz||64MB||256-bit||16GB||GDDR6X||22.5|
320W(TGP)/ 516W (Max TGP)
|RTX 4070 Ti (4080 12GB Revamped)||AD104-400-A1||7680||60||2.61GHz||48MB||192-bit||12GB||GDDR6X||21|
285W (TGP) /366W (Max TGP)?
|RTX 4060 Ti||AD104||6656||52||3.2 GHz?||40MB?||160-bit||10GB||GDDR6X (?)||18||200W|
|RTX 4060||AD106||4352||34||3.0 GHz?||32MB||128-bit||8GB||GDDR6X (?)||18||180W|