NVIDIA DGX Spark vs M1 Pro 32GB for local LLMs
57 reports on the NVIDIA DGX Spark and 2 on the M1 Pro 32GB
Which is faster for local LLMs?
On Qwen3.6 35B · 3B active at 4-bit, the NVIDIA DGX Spark runs at 78.3 tokens per second (one run) and the M1 Pro 32GB at 25.4 (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 33% higher on the NVIDIA DGX Spark (273 GB/s on the NVIDIA DGX Spark, 205 on the M1 Pro 32GB).
- Memory
- 128GB unified
- Memory bandwidth
- 273 GB/s
- FP16 compute
- 125 TFLOPS
- Reports
- 57
- Memory
- 32GB unified
- Memory bandwidth
- 205 GB/s
- FP16 compute
- 5.2 TFLOPS
- Reports
- 2
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 quant level. Engines and context lengths can still differ between the runs. How to read these
| Model | NVIDIA DGX Spark | M1 Pro 32GB |
|---|---|---|
| Qwen3.6 35B · 3B active4-bit | 78.3one run | 25.4one run |
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 | M1 Pro 32GB |
|---|---|---|
| Qwen3.6 35B · 3B active | 14.5 t/sFP16 | 40.7 t/sQ3_K_M |
| Qwen3.8 27B | 4.0 t/sFP16 | 11.2 t/sQ4_K_S |
| Qwen3.8 125B · 6B active | 14.4 t/sQ6_K | doesn't fit at these settings |
| DeepSeek V4 Flash 284B · 13B active | 38.3 t/sQ2_K | doesn't fit at these settings |
| Qwen3.6 27B | 4.0 t/sFP16 | 11.2 t/sQ4_K_S |
| Gemma 4 26B · 4B active | 10.8 t/sFP16 | 24.6 t/sQ4_K_M |
| 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 · M1 Pro 32GB
Every report on each card, with its source: NVIDIA DGX Spark · M1 Pro 32GB