Head to head

RTX 5090 vs Radeon RX 7900 XTX

The RTX 5090 holds more — 32 GB against 24 GB — which decides what you can load at all. The RTX 5090 has more bandwidth at 1792 GB/s, which decides how fast tokens come out once a model fits.

Model (Q4_K_M, 8K)RTX 5090tok/sRadeon RX 7900 XTXtok/s
Llama 3.1 8B Runs comfortably 222 Runs comfortably 105
Llama 3.1 70B Won't fit 2.65 Won't fit 1.52
Llama 3.2 3B Runs comfortably 478 Runs comfortably 230
Llama 3.2 1B Runs comfortably 1235 Runs comfortably 609
Llama 4 Scout 109B-A17B Won't fit 6.75 Won't fit 4.91
Qwen3 8B Runs comfortably 214 Runs comfortably 101
Qwen3 14B Runs comfortably 126 Runs comfortably 59.3
Qwen3 32B Runs comfortably 59.0 Fits, but tight 27.6
Qwen3 4B Runs comfortably 380 Runs comfortably 183
Qwen3 30B-A3B Runs comfortably 159 Runs comfortably 112
Qwen3 235B-A22B Won't fit 3.83 Won't fit 3.07
Qwen2.5-Coder 32B Runs comfortably 59.0 Fits, but tight 27.6
Qwen2.5 7B Runs comfortably 247 Runs comfortably 116
Qwen2.5 72B Won't fit 2.50 Won't fit 1.44
Gemma 3 4B Runs comfortably 405 Runs comfortably 196
Gemma 3 12B Runs comfortably 151 Runs comfortably 71.1

Specifications

RTX 5090Radeon RX 7900 XTX
Memory32 GB24 GB
Bandwidth1792 GB/s960 GB/s
FP16 compute209 TFLOPS123 TFLOPS
Launch price$1,999$999
ArchitectureBlackwellRDNA3