llamaperf
Submit

RTX 5090 vs RX 7900 GRE 16GB

For running local LLMs · 65 reports across 11 models

Side A
RTX 5090
Vendor
nvidia
VRAM
32GB
Memory
Discrete
Side B
RX 7900 GRE 16GB
Vendor
amd
VRAM
16GB
Memory
Discrete

Highest reported generation speed by model family

These maxima come from different community setups. Model size, quantization, GPU count, offloading and concurrency may differ. They do not establish which GPU is faster for the same workload. Check the comparison conditions →

ModelRTX 5090RX 7900 GRE 16GB
Qwen3.8up to 2400B220.0n=34—
DeepSeek V4 Flashup to 285B120.0n=10—
Qwen3.6up to 35B215.1n=6—
Gemma 4up to 31B578.0n=451.9n=1
Museup to 30B253.0n=4—
GLM-5.2up to 744B—n=1—
GLM-5.324.5n=1—
Kimi K2.5—n=1—
Qwen2.5up to 32B—n=1—
Qwen3up to 235B159.0n=1—
Qwen3.5up to 122B—n=1—

More comparisons