NVIDIA DGX Spark vs NVIDIA L4 for local LLMs
87 reports on the NVIDIA DGX Spark and 3 on the NVIDIA L4
Which is faster for local LLMs?
On Qwen3.8 27B at 4-bit, the NVIDIA DGX Spark has generation speed not reported; prompt processing 899.9 tokens/s (one run); the NVIDIA L4 has 14.6 generation tokens/s (one run). Memory bandwidth, which caps how fast a card can write, is 10% higher on the NVIDIA L4 (273 GB/s on the NVIDIA DGX Spark, 300 on the NVIDIA L4).
- Memory
- 128GB unified
- Memory bandwidth
- 273 GB/s
- FP16 compute
- 125 TFLOPS
- Reports
- 87
- Memory
- 24GB
- Memory bandwidth
- 300 GB/s
- FP16 compute
- 121 TFLOPS
- Reports
- 3
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 L4 |
|---|---|---|
| Qwen3.8 27B4-bit | -0 runsPP 899.9 (one run)llama.cpp16K context | 14.6one runllama.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 L4 |
|---|---|---|
| Qwen3.8 27B | 4.0 t/sFP16 | 10.9 t/sQ4_K_M |
| Qwen3.8 125B · 6B active | 14.4 t/sQ6_K | 16.4 t/sQ2_K, experts in RAM |
| Qwen3.6 35B · 3B active | 14.5 t/sFP16 | 38.5 t/sQ4_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 | 10.9 t/sQ4_K_M |
| Gemma 4 26B · 4B active | 10.8 t/sFP16 | 24.5 t/sQ5_K_S |
| 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 L4
Every report on each card, with its source: NVIDIA DGX Spark · NVIDIA L4