NVIDIA DGX Spark vs NVIDIA Jetson AGX Thor 128GB for local LLMs
99 reports on the NVIDIA DGX Spark and 8 on the NVIDIA Jetson AGX Thor 128GB
Which is faster for local LLMs?
On Qwen3.8 125B · 6B active at 4-bit, the NVIDIA DGX Spark has 29.8 generation tokens/s (2 runs); the NVIDIA Jetson AGX Thor 128GB has 36.7 generation tokens/s (one run); prompt processing 899.0 tokens/s (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 about the same on both (273 GB/s on the NVIDIA DGX Spark, 273 on the NVIDIA Jetson AGX Thor 128GB). Across 1 shared models with generation measurements on both cards, the NVIDIA DGX Spark's median is higher on 0 and the NVIDIA Jetson AGX Thor 128GB's on 1.
- Memory
- 128GB unified
- Memory bandwidth
- 273 GB/s
- FP16 compute
- 125 TFLOPS
- Reports
- 99
- Memory
- 128GB unified
- Memory bandwidth
- 273 GB/s
- FP16 compute
- 258.8 TFLOPS
- Reports
- 8
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 Jetson AGX Thor 128GB |
|---|---|---|
| Qwen3.8 125B · 6B active4-bit | 29.82 runsllama.cpp, SGLang128K to 256K context | 36.7one runPP 899.0 (one run)engine not stated256K context |
| Qwen3.8 27B4-bit | -0 runsPP 899.9 (one run)llama.cpp16K context | 12.0one runengine not statedcontext 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 Jetson AGX Thor 128GB |
|---|---|---|
| Qwen3.8 125B · 6B active | 14.4 t/sQ6_K | 10.0 t/sQ6_K |
| Qwen3.8 27B | 4.0 t/sFP16 | 2.8 t/sFP16 |
| Qwen3.6 35B · 3B active | 14.5 t/sFP16 | 10.0 t/sFP16 |
| DeepSeek V4 Flash 284B · 13B active | 38.3 t/sQ2_K | 26.5 t/sQ2_K |
| 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 | 2.8 t/sFP16 |
| Gemma 4 26B · 4B active | 10.8 t/sFP16 | 7.5 t/sFP16 |
| GLM-5.3 320B · 18B active | 12.7 t/sQ2_K | 8.8 t/sQ2_K |
Change the context, RAM or model in the calculator: NVIDIA DGX Spark · NVIDIA Jetson AGX Thor 128GB
Every report on each card, with its source: NVIDIA DGX Spark · NVIDIA Jetson AGX Thor 128GB