NVIDIA RTX 5090 vs AMD RX 7900 GRE 16GB for local LLMs
162 reports on the NVIDIA RTX 5090 and 3 on the AMD RX 7900 GRE 16GB
Which is faster for local LLMs?
Nobody has reported the same model at the same quant on both cards yet, so there's no measured head-to-head. Memory bandwidth, which caps how fast a card can write, is 3.1x higher on the NVIDIA RTX 5090 (1,792 GB/s on the NVIDIA RTX 5090, 576 on the AMD RX 7900 GRE 16GB). The estimates below compare them on the models people run most.
NVIDIA RTX 5090
- Memory
- 32GB
- Memory bandwidth
- 1,792 GB/s
- FP16 compute
- 419 TFLOPS
- Reports
- 162
AMD RX 7900 GRE 16GB
- Memory
- 16GB
- Memory bandwidth
- 576 GB/s
- FP16 compute
- 46 TFLOPS
- Reports
- 3
Estimated by the calculator
The quant the calculator recommends for each card and its estimated speed at a 32,768-token context with 32 GB of system RAM, from memory bandwidth and the model's shape.
| Model | NVIDIA RTX 5090 | AMD RX 7900 GRE 16GB |
|---|---|---|
| Qwen3.8 27B | 44.9 t/sQ6_K | 37.5 t/sQ2_K |
| Qwen3.8 125B · 6B active | 20.3 t/sQ2_K, experts in RAM | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 163.0 t/sQ5_K_M | 124.2 t/sQ2_K |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 44.9 t/sQ6_K | 37.5 t/sQ2_K |
| Gemma 4 26B · 4B active | 114.5 t/sQ6_K | 83.7 t/sQ3_K_S |
Change the context, RAM or model in the calculator: NVIDIA RTX 5090 · AMD RX 7900 GRE 16GB
Every report on each card, with its source: NVIDIA RTX 5090 · AMD RX 7900 GRE 16GB