NVIDIA DGX Spark vs NVIDIA RTX 4090 for local LLMs
71 reports on the NVIDIA DGX Spark and 41 on the NVIDIA RTX 4090
Which is faster for local LLMs?
On Gemma 4 26B · 4B active at 4-bit, the NVIDIA DGX Spark runs at 59.1 tokens per second (2 runs) and the NVIDIA RTX 4090 at 149.6 (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 3.7x higher on the NVIDIA RTX 4090 (273 GB/s on the NVIDIA DGX Spark, 1,008 on the NVIDIA RTX 4090).
- Memory
- 128GB unified
- Memory bandwidth
- 273 GB/s
- FP16 compute
- 125 TFLOPS
- Reports
- 71
- Memory
- 24GB
- Memory bandwidth
- 1,008 GB/s
- FP16 compute
- 330 TFLOPS
- Reports
- 41
Measured on both
Median tokens per second 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 4090 |
|---|---|---|
| Gemma 4 26B · 4B active4-bit | 59.12 runsllama.cpp, vLLM256K context, 1 not stated | 149.6one runOllamacontext 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 4090 |
|---|---|---|
| Gemma 4 26B · 4B active | 10.8 t/sFP16 | 82.3 t/sQ5_K_S |
| Qwen3.8 27B | 4.0 t/sFP16 | 36.5 t/sQ4_K_M |
| Qwen3.8 125B · 6B active | 14.4 t/sQ6_K | 19.6 t/sQ2_K, experts in RAM |
| DeepSeek V4 Flash 284B · 13B active | 38.3 t/sQ2_K | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 14.5 t/sFP16 | 129.3 t/sQ4_K_S |
| Qwen3.6 27B | 4.0 t/sFP16 | 36.5 t/sQ4_K_M |
| GLM-5.3 320B · 18B active | 12.7 t/sQ2_K | doesn't fit at these settings |
Change the context, RAM or model in the calculator: NVIDIA DGX Spark · NVIDIA RTX 4090
Every report on each card, with its source: NVIDIA DGX Spark · NVIDIA RTX 4090