Side-by-side GPU comparison: specs, memory, compute performance, and live cloud pricing.
Verdict
RTX 3090 has 8 GB more VRAM, making it better suited for large models and long context windows. For compute-bound workloads like training, RX 9070 XT delivers 2.7× higher FP16 throughput. RTX 3090 supports a broader range of models (566 vs 502 from this catalog), giving more flexibility.
Specifications
| RTX 3090 | RX 9070 XT | |
|---|---|---|
| VRAM | 24 GB | 16 GB |
| VRAM Type | GDDR6X | GDDR6 |
| Memory Bandwidth | 0.9 TB/s | 0.6 TB/s |
| FP16 Performance | 71 TFLOPS | 195 TFLOPS |
| Manufacturer | NVIDIA | AMD |
| FP8 Support | No | Yes |
| FP4 Support | No | No |
Price / Performance
Based on cheapest single-GPU on-demand pricing. Lower $/TFLOP = better compute value; lower $/GB = better memory value.
| RTX 3090 | RX 9070 XT | |
|---|---|---|
| $/hr (cheapest) | $0.25 | — |
| $/TFLOP (compute value) | $0.0035 | — |
| $/GB VRAM (memory value) | $0.0104 | — |
Cloud Pricing
Cheapest on-demand price per provider (single GPU).
Model Compatibility
Models from the catalog that fit on each GPU, grouped by required precision.
RTX 3090 (566 models)
RX 9070 XT (502 models)
You might also compare…
Pricing data refreshed hourly · Last updated April 11, 2026 · Browse all comparisons