AMD RX 6900 XT 16GB vs AMD RX 7900 XT for local LLMs
2 reports on the AMD RX 6900 XT 16GB and 5 on the AMD RX 7900 XT
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 1.6x higher on the AMD RX 7900 XT (512 GB/s on the AMD RX 6900 XT 16GB, 800 on the AMD RX 7900 XT). The estimates below compare them on the models people run most.
AMD RX 6900 XT 16GB
- Memory
- 16GB
- Memory bandwidth
- 512 GB/s
- FP16 compute
- 46.1 TFLOPS
- Reports
- 2
AMD RX 7900 XT
- Memory
- 20GB
- Memory bandwidth
- 800 GB/s
- FP16 compute
- 103 TFLOPS
- Reports
- 5
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 | AMD RX 6900 XT 16GB | AMD RX 7900 XT |
|---|---|---|
| Qwen3.8 27B | 33.4 t/sQ2_K | 37.2 t/sQ3_K_M |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | 19.2 t/sQ2_K, experts in RAM |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 110.4 t/sQ2_K | 147.9 t/sQ3_K_S |
| Qwen3.6 27B | 33.4 t/sQ2_K | 37.2 t/sQ3_K_M |
| Gemma 4 26B · 4B active | 74.4 t/sQ3_K_S | 83.9 t/sQ4_K_S |
Change the context, RAM or model in the calculator: AMD RX 6900 XT 16GB · AMD RX 7900 XT
Every report on each card, with its source: AMD RX 6900 XT 16GB · AMD RX 7900 XT