NVIDIA DGX Spark vs NVIDIA Rubin 288GB for local LLMs
57 reports on the NVIDIA DGX Spark and 0 on the NVIDIA Rubin 288GB
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 80.6x higher on the NVIDIA Rubin 288GB (273 GB/s on the NVIDIA DGX Spark, 22,000 on the NVIDIA Rubin 288GB). 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
- 57
NVIDIA Rubin 288GB
- Memory
- 288GB
- Memory bandwidth
- 22,000 GB/s
- FP16 compute
- 4000 TFLOPS
- Reports
- 0
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 | NVIDIA Rubin 288GB |
|---|---|---|
| Qwen3.8 27B | 4.0 t/sFP16 | 224.1 t/sFP16 |
| Qwen3.8 125B · 6B active | 14.4 t/sQ6_K | 806.7 t/sQ8_0 |
| DeepSeek V4 Flash 284B · 13B active | 38.3 t/sQ2_K | 726.3 t/sQ6_K |
| Qwen3.6 35B · 3B active | 14.5 t/sFP16 | 806.7 t/sFP16 |
| Qwen3.6 27B | 4.0 t/sFP16 | 224.1 t/sFP16 |
| Gemma 4 26B · 4B active | 10.8 t/sFP16 | 605.0 t/sFP16 |
Change the context, RAM or model in the calculator: NVIDIA DGX Spark · NVIDIA Rubin 288GB
Every report on each card, with its source: NVIDIA DGX Spark · NVIDIA Rubin 288GB