AMD RX 6950 XT vs AMD RX 7900 XT for local LLMs
0 reports on the AMD RX 6950 XT and 13 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 39% higher on the AMD RX 7900 XT (576 GB/s on the AMD RX 6950 XT, 800 on the AMD RX 7900 XT). The estimates below compare them on the models people run most.
AMD RX 6950 XT
- Memory
- 16GB
- Memory bandwidth
- 576 GB/s
- FP16 compute
- 47.3 TFLOPS
- Reports
- 0
AMD RX 7900 XT
- Memory
- 20GB
- Memory bandwidth
- 800 GB/s
- FP16 compute
- 103 TFLOPS
- Reports
- 13
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 6950 XT | AMD RX 7900 XT |
|---|---|---|
| Qwen3.8 27B | 37.5 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 |
| Qwen3.6 35B · 3B active | 124.2 t/sQ2_K | 147.9 t/sQ3_K_S |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 37.5 t/sQ2_K | 37.2 t/sQ3_K_M |
| Gemma 4 26B · 4B active | 83.7 t/sQ3_K_S | 83.9 t/sQ4_K_S |
Change the context, RAM or model in the calculator: AMD RX 6950 XT · AMD RX 7900 XT
Every report on each card, with its source: AMD RX 6950 XT · AMD RX 7900 XT