llamaperf
Submit

RTX 5090 vs RX 9070

For running local LLMs · 12 reports across 3 models

Side A
RTX 5090
Vendor
nvidia
VRAM
32GB
Memory
Discrete
Side B
RX 9070
Vendor
amd
VRAM
16GB
Memory
Discrete

Tokens per second by model

ModelRTX 5090RX 9070
Qwen3.6up to 35B3238.0n=746.9n=1
Gemma 4up to 31B578.0n=3—
Qwen2.5—n=1—

More comparisons