NVIDIA DGX Spark vs AMD RX 7900 XT for local LLMs
87 reports on the NVIDIA DGX Spark and 10 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 2.9x higher on the AMD RX 7900 XT (273 GB/s on the NVIDIA DGX Spark, 800 on the AMD RX 7900 XT). The estimates below compare them on the models people run most.
NVIDIA DGX Spark
- Memory
- 128GB unified
- Memory bandwidth
- 273 GB/s
- FP16 compute
- 125 TFLOPS
- Reports
- 87
AMD RX 7900 XT
- Memory
- 20GB
- Memory bandwidth
- 800 GB/s
- FP16 compute
- 103 TFLOPS
- Reports
- 10
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 DGX Spark | AMD RX 7900 XT |
|---|---|---|
| Qwen3.8 27B | 4.0 t/sFP16 | 37.2 t/sQ3_K_M |
| Qwen3.8 125B · 6B active | 14.4 t/sQ6_K | 19.2 t/sQ2_K, experts in RAM |
| Qwen3.6 35B · 3B active | 14.5 t/sFP16 | 147.9 t/sQ3_K_S |
| DeepSeek V4 Flash 284B · 13B active | 38.3 t/sQ2_K | doesn't fit at these settings |
| Qwen3.6 27B | 4.0 t/sFP16 | 37.2 t/sQ3_K_M |
| Gemma 4 26B · 4B active | 10.8 t/sFP16 | 83.9 t/sQ4_K_S |
Change the context, RAM or model in the calculator: NVIDIA DGX Spark · AMD RX 7900 XT
Every report on each card, with its source: NVIDIA DGX Spark · AMD RX 7900 XT