NVIDIA DGX Spark vs M5 Ultra 256GB for local LLMs
87 reports on the NVIDIA DGX Spark and 28 on the M5 Ultra 256GB
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 M5 Ultra 256GB has 50.0 generation tokens/s (one run); prompt processing 1800.0 tokens/s (one run). Memory bandwidth, which caps how fast a card can write, is 4.5x higher on the M5 Ultra 256GB (273 GB/s on the NVIDIA DGX Spark, 1,229 on the M5 Ultra 256GB).
- Memory
- 128GB unified
- Memory bandwidth
- 273 GB/s
- FP16 compute
- 125 TFLOPS
- Reports
- 87
- Memory
- 256GB unified
- Memory bandwidth
- 1,229 GB/s
- FP16 compute
- not on record
- Reports
- 28
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 | M5 Ultra 256GB |
|---|---|---|
| Qwen3.8 27B4-bit | -0 runsPP 899.9 (one run)llama.cpp16K context | 50.0one runPP 1800.0 (one run)oMLX8K context |
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 | M5 Ultra 256GB |
|---|---|---|
| Qwen3.8 27B | 4.0 t/sFP16 | 14.9 t/sFP16 |
| Qwen3.8 125B · 6B active | 14.4 t/sQ6_K | 50.8 t/sQ8_0 |
| Qwen3.6 35B · 3B active | 14.5 t/sFP16 | 53.5 t/sFP16 |
| DeepSeek V4 Flash 284B · 13B active | 38.3 t/sQ2_K | 66.9 t/sQ4_K_M |
| Qwen3.6 27B | 4.0 t/sFP16 | 14.9 t/sFP16 |
| Gemma 4 26B · 4B active | 10.8 t/sFP16 | 40.1 t/sFP16 |
| DeepSeek V4.1 Flash 552B · 16B active | doesn't fit at these settings | 89.4 t/sQ2_K |
Change the context, RAM or model in the calculator: NVIDIA DGX Spark · M5 Ultra 256GB
Every report on each card, with its source: NVIDIA DGX Spark · M5 Ultra 256GB