Launch MSRPs, release cycles and deals windows as of November 9, 2026.
This is a cross-brand comparison between the AMD RX 9070 GRE (RX 9000, High-end, current generation) and the NVIDIA RTX 4080 Super (RTX 4000, Enthusiast, superseded by the NVIDIA RTX 5080), released 2 years 4 months apart. Against the RTX 4080 Super, the RX 9070 GRE costs $450 less at launch MSRP ($549 vs $999, 45% cheaper), has 4 GB less VRAM (12 GB vs 16 GB) and draws 100W less at rated TDP (220W vs 320W).
Early in cycle — strong buy, no urgency to wait
Best for: 1440p gamers who want RDNA 4 and FSR 4 and can find the GRE meaningfully cheaper than the 16GB RX 9070.
Full details →This GPU is no longer the current generation. It has been replaced by the NVIDIA RTX 5080.
Superseded by RTX 5080
Best for: 4K gamers who can find a well-priced used unit, understanding they miss out on DLSS 4 and Blackwell's efficiency gains.
Full details →| AMD RX 9070 GRE | NVIDIA RTX 4080 Super | |
|---|---|---|
| Tier | High-end | Enthusiast |
| Generation | RX 9000 | RTX 4000 |
| VRAM | 12 GB | 16 GB |
| Memory Type | GDDR6 | GDDR6X |
| TDP | 220W | 320W |
| Upscaling | FSR4 | DLSS3 |
| Ray Tracing | ✅ | ✅ |
| Launch MSRP | $549 | $999 |
| Editor score | 7.8/10 | 8.4/10 |
| Released | Jun 2, 2026 | Jan 31, 2024 |
| Cycle length | ~367 days | ~365 days |
| Cycle advice | Buy | Superseded |
| Deals advice | Caution | Clearance |
| Successor | — | RTX 5080 |
Full access to AMD's ML-based FSR 4 upscaling and RDNA 4's improved ray tracing.
AMD claims up to 22% higher performance than the 16GB RTX 5060 Ti across 40+ games.
Enough VRAM for 1440p today, though less headroom than the 16GB RX 9070 and RX 9070 XT.
New units sell around $1,400–$1,600 and used units start around $1,100 as of October 2026 — both above the $999 MSRP. Only worth it if a used unit turns up well below MSRP.
Ample VRAM for 4K gaming and content creation.
Over 2 years of optimizations ensures stability across all titles.
Released Jun 2, 2026, the RX 9070 GRE has been on the market for 5 months. The previous cycle for this line ran about 367 days, so it is roughly 44% of the way through a typical cycle, with around 207 days to go before a replacement would be due on past form. Our model rates it Buy.
Released Jan 31, 2024, the RTX 4080 Super has been on the market for 2 years 9 months. It has been superseded by the NVIDIA RTX 5080, which launched Jan 30, 2025, so it's no longer a current-generation buy — new stock is clearance, and the rest of the market is second-hand.
On timing, the RX 9070 GRE is the only current-generation option of the two (Buy), while the RTX 4080 Super is a clearance or used purchase.
At launch MSRP the RX 9070 GRE is $450 cheaper than the RTX 4080 Super ($549 vs $999, 45% less). Per gigabyte of VRAM that's $45.8 for the RX 9070 GRE and $62.4 for the RTX 4080 Super — the RX 9070 GRE gives more memory for the money. Launch MSRP is only a reference point for a superseded card; its real price is whatever clearance or used stock sells for today.
RX 9070 GRE (deals window to Dec 5, 2026, rated Caution): Black Friday / Cyber Monday 2026 — another AMD price increase was reported for November, so deep discounts are unlikely. Only buy well below the RX 9070's street price.
RTX 4080 Super (deals window to Jun 30, 2027, rated Wait): No clearance — new retail prices are ~40–60% above $999 MSRP due to production ending and scarcity, and used units start around $1,100 as of October 2026. Only consider a used unit well below MSRP.
Next on the deals calendar: for the RX 9070 GRE, New Year clearance 2027, from Jan 2, 2027 to Jan 20, 2027.
Our pick: AMD RX 9070 GRE
Our pick is the RX 9070 GRE: it's the current-generation card here, while the RTX 4080 Super has been superseded by the NVIDIA RTX 5080, and it also costs $450 less at launch MSRP ($549 vs $999) and draws 100W less at rated TDP (220W vs 320W).
Go for the RTX 4080 Super instead if you want more VRAM: 16 GB vs 12 GB, or if you want newer GDDR6X memory rather than GDDR6.
Buy/Wait and deals ratings come from release-cycle and pricing data, not benchmarks. How we rate →