NVIDIA DGX Spark vs NVIDIA RTX 5070 Ti for local LLMs
87 reports on the NVIDIA DGX Spark and 50 on the NVIDIA RTX 5070 Ti
Which is faster for local LLMs?
On Gemma 4 26B · 4B active at 4-bit, the NVIDIA DGX Spark has 59.1 generation tokens/s (2 runs); prompt processing 2657.0 tokens/s (one run); the NVIDIA RTX 5070 Ti has 137.7 generation tokens/s (one run); prompt processing 5951.0 tokens/s (one run). Those are community reports whose engines and settings differ, so the gap is a rough sign, not a controlled measure of the two cards. Memory bandwidth, which caps how fast a card can write, is 3.3x higher on the NVIDIA RTX 5070 Ti (273 GB/s on the NVIDIA DGX Spark, 896 on the NVIDIA RTX 5070 Ti).
- Memory
- 128GB unified
- Memory bandwidth
- 273 GB/s
- FP16 compute
- 125 TFLOPS
- Reports
- 87
- Memory
- 16GB
- Memory bandwidth
- 896 GB/s
- FP16 compute
- 176 TFLOPS
- Reports
- 50
Measured on both
Generation and prompt processing speeds from plain runs (one device, one request, no speculative decoding, the whole model in the device's memory) of the same model size at the same bit class. Each side shows the engines and reported context behind its median. Context can mean a configured window or prompt depth, so these are community comparisons with differing settings. How to read these
| Model | NVIDIA DGX Spark | NVIDIA RTX 5070 Ti |
|---|---|---|
| Gemma 4 26B · 4B active4-bit | 59.12 runsPP 2657.0 (one run)llama.cpp, vLLM256K context, 1 not stated | 137.7one runPP 5951.0 (one run)llama.cppcontext not stated |
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. Where a model was also measured above, the measurement wins.
| Model | NVIDIA DGX Spark | NVIDIA RTX 5070 Ti |
|---|---|---|
| Gemma 4 26B · 4B active | 10.8 t/sFP16 | 130.3 t/sQ3_K_S |
| Qwen3.8 27B | 4.0 t/sFP16 | 58.4 t/sQ2_K |
| Qwen3.8 125B · 6B active | 14.4 t/sQ6_K | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 14.5 t/sFP16 | 193.2 t/sQ2_K |
| DeepSeek V4 Flash 284B · 13B active | 38.3 t/sQ2_K | doesn't fit at these settings |
| Qwen3.6 27B | 4.0 t/sFP16 | 58.4 t/sQ2_K |
| DeepSeek V4.1 Flash 552B · 16B active | doesn't fit at these settings | doesn't fit at these settings |
Change the context, RAM or model in the calculator: NVIDIA DGX Spark · NVIDIA RTX 5070 Ti
Every report on each card, with its source: NVIDIA DGX Spark · NVIDIA RTX 5070 Ti