NVIDIA DGX Spark vs AMD Strix Halo 128GB for local LLMs
71 reports on the NVIDIA DGX Spark and 113 on the AMD Strix Halo 128GB
Which is faster for local LLMs?
On Qwen3.8 125B · 6B active at 4-bit, the NVIDIA DGX Spark runs at 29.8 tokens per second (2 runs) and the AMD Strix Halo 128GB at 22.0 (4 runs). 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 7% higher on the NVIDIA DGX Spark (273 GB/s on the NVIDIA DGX Spark, 256 on the AMD Strix Halo 128GB).
- Memory
- 128GB unified
- Memory bandwidth
- 273 GB/s
- FP16 compute
- 125 TFLOPS
- Reports
- 71
- Memory
- 128GB unified
- Memory bandwidth
- 256 GB/s
- FP16 compute
- 59 TFLOPS
- Reports
- 113
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 | AMD Strix Halo 128GB |
|---|---|---|
| Qwen3.8 125B · 6B active4-bit | 29.82 runsllama.cpp, SGLang128K to 256K context | 22.04 runsGufo, llama.cpp128K to 160K 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 | AMD Strix Halo 128GB |
|---|---|---|
| Qwen3.8 125B · 6B active | 14.4 t/sQ6_K | 12.6 t/sQ6_K |
| Qwen3.8 27B | 4.0 t/sFP16 | 3.5 t/sFP16 |
| DeepSeek V4 Flash 284B · 13B active | 38.3 t/sQ2_K | 33.5 t/sQ2_K |
| Qwen3.6 35B · 3B active | 14.5 t/sFP16 | 12.6 t/sFP16 |
| Qwen3.6 27B | 4.0 t/sFP16 | 3.5 t/sFP16 |
| GLM-5.3 320B · 18B active | 12.7 t/sQ2_K | 11.1 t/sQ2_K |
| Gemma 4 26B · 4B active | 10.8 t/sFP16 | 9.5 t/sFP16 |
Change the context, RAM or model in the calculator: NVIDIA DGX Spark · AMD Strix Halo 128GB
Every report on each card, with its source: NVIDIA DGX Spark · AMD Strix Halo 128GB