NVIDIA DGX Spark vs M5 Ultra 96GB for local LLMs
99 reports on the NVIDIA DGX Spark and 12 on the M5 Ultra 96GB
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 4.5x higher on the M5 Ultra 96GB (273 GB/s on the NVIDIA DGX Spark, 1,229 on the M5 Ultra 96GB). 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
- 99
M5 Ultra 96GB
- Memory
- 96GB unified
- Memory bandwidth
- 1,229 GB/s
- FP16 compute
- not on record
- Reports
- 12
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 | M5 Ultra 96GB |
|---|---|---|
| Qwen3.8 27B | 4.0 t/sFP16 | 14.9 t/sFP16 |
| Qwen3.8 125B · 6B active | 14.4 t/sQ6_K | 103.1 t/sQ3_K_M |
| Qwen3.6 35B · 3B active | 14.5 t/sFP16 | 107.0 t/sQ8_0 |
| DeepSeek V4 Flash 284B · 13B active | 38.3 t/sQ2_K | doesn't fit at these settings |
| DeepSeek V4.1 Flash 552B · 16B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 4.0 t/sFP16 | 14.9 t/sFP16 |
Change the context, RAM or model in the calculator: NVIDIA DGX Spark · M5 Ultra 96GB
Every report on each card, with its source: NVIDIA DGX Spark · M5 Ultra 96GB