MI300X OAM vs RTX 5090 SE
Head-to-head specifications
| Metric | MI300X OAM | RTX 5090 SE | Difference |
|---|---|---|---|
| FP32 compute (TFLOPS) | 90.3 | 66.9 | +34.8% |
| VRAM | 192 GB HBM3 | 24 GB GDDR7 | — |
| Memory bandwidth (GB/s) | 5,300 | 1,344 | +294.3% |
| TDP (W) | 750 | 500 | — |
| Stable Diffusion (it/s) | 110.0 | 26.8 | +310.4% |
| LLM inference (tokens/s) | 420 | 107 | +292.5% |
| Launch MSRP (USD) | $20,000 | $1,499 | +1,234.2% |
- MI300X OAM offers 90.3 TFLOPS of FP32 compute versus 66.9. These cards span different eras or segments, so modern gaming benchmarks are not directly comparable — judge them within their own generation and use case.
Verdict: MI300X OAM or RTX 5090 SE?
MI300X OAM advantages
- Video memory (+88%)
- Memory bandwidth (+75%)
- AI image generation (+76%)
- Local LLM inference (+75%)
RTX 5090 SE advantages
- Power efficiency (+33%)
- Affordability (+93%)
Which should you choose?
- Choose the MI300X OAM if you play the latest titles at high textures or do GPU-accelerated work.
- Choose the RTX 5090 SE if you want lower power draw, heat and noise.
- Choose the MI300X OAM if you work with high-resolution textures or memory-bound workloads.
MI300X OAM vs RTX 5090 SE: which should you choose?
MI300X OAM — AMD server graphics card (2023, CDNA 3.0) with 192 GB of HBM3; launched at $20,000.
RTX 5090 SE — NVIDIA desktop graphics card (2026, Blackwell) with 24 GB of GDDR7, averaging 126 fps at 1440p; launched at $1,499.
MI300X OAM vs RTX 5090 SE: MI300X OAM has more raw compute. MI300X OAM offers 90.3 TFLOPS of FP32 compute versus 66.9. These cards span different eras or segments, so modern gaming benchmarks are not directly comparable — judge them within their own generation and use case.
Different eras, different missions
These two parts do not compete head-to-head: MI300X OAM (2023, Server) and RTX 5090 SE (2026, Desktop) come from different generations or market segments, so modern game benchmarks do not apply to both. The specification table above is best read as architectural context — process node, memory technology and power budgets show how far GPU design has moved.
Specifications at a glance
MI300X OAM carries 192 GB of HBM3 against 24 GB of GDDR7 on RTX 5090 SE, with board powers of 750 W and 500 W respectively.
The verdict
Both are credible choices in the graphics card comparison space; the specification table above lays out every metric so you can weigh the trade-offs that matter to you. Pick the one whose strengths line up with how you will actually use it.
Frequently asked questions
Is the MI300X OAM better than the RTX 5090 SE?
MI300X OAM takes the overall edge, though RTX 5090 SE wins in specific areas worth weighing. MI300X OAM offers 90.3 TFLOPS of FP32 compute versus 66.9. These cards span different eras or segments, so modern gaming benchmarks are not directly comparable — judge them within their own generation and use case.
What is the main difference between the MI300X OAM and the RTX 5090 SE?
MI300X OAM offers 90.3 TFLOPS of FP32 compute versus 66.9. These cards span different eras or segments, so modern gaming benchmarks are not directly comparable — judge them within their own generation and use case.
Which should I choose?
Choose the MI300X OAM if you play the latest titles at high textures or do GPU-accelerated work. Choose the RTX 5090 SE if you want lower power draw, heat and noise.
Methodology
Graphics cards are compared on 3DMark Time Spy scores, average gaming frame rates at 1080p/1440p/4K, FP32 compute throughput, VRAM capacity and type, memory bandwidth, board power (TDP) and launch MSRP — plus AI workload throughput (Stable Diffusion iterations/s and local LLM tokens/s) where measured. Vintage and server GPUs without modern benchmark results are compared on specifications only, clearly labelled. Frame rates are averages across a game suite at high settings; specific titles vary.