NVIDIA DGX Spark vs AMD Gorgon Halo 192GB for local LLMs
99 reports on the NVIDIA DGX Spark and 8 on the AMD Gorgon Halo 192GB
Which is faster for local LLMs?
On gpt-oss 117B · 5.1B active at 4-bit, the NVIDIA DGX Spark has 52.9 generation tokens/s (one run); prompt processing 1689.5 tokens/s (one run); the AMD Gorgon Halo 192GB has 49.0 generation tokens/s (2 runs); prompt processing 760.0 tokens/s (2 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 about the same on both (273 GB/s on the NVIDIA DGX Spark, 273 on the AMD Gorgon Halo 192GB).
- Memory
- 128GB unified
- Memory bandwidth
- 273 GB/s
- FP16 compute
- 125 TFLOPS
- Reports
- 99
- Memory
- 192GB unified
- Memory bandwidth
- 273 GB/s
- FP16 compute
- 61.4 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 | AMD Gorgon Halo 192GB |
|---|---|---|
| gpt-oss 117B · 5.1B active4-bit | 52.9one runPP 1689.5 (one run)llama.cppcontext not stated | 49.02 runsPP 760.0 (2 runs)llama.cpp512 context, 1 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 | AMD Gorgon Halo 192GB |
|---|---|---|
| gpt-oss 117B · 5.1B active | 18.0 t/sQ6_K | 11.7 t/sQ8_0 |
| Qwen3.8 27B | 4.0 t/sFP16 | 2.8 t/sFP16 |
| Qwen3.8 125B · 6B active | 14.4 t/sQ6_K | 9.5 t/sQ8_0 |
| Qwen3.6 35B · 3B active | 14.5 t/sFP16 | 10.0 t/sFP16 |
| DeepSeek V4 Flash 284B · 13B active | 38.3 t/sQ2_K | 12.5 t/sQ4_K_M |
| DeepSeek V4.1 Flash 552B · 16B active | doesn't fit at these settings | 16.7 t/sQ2_K |
| Qwen3.6 27B | 4.0 t/sFP16 | 2.8 t/sFP16 |
Change the context, RAM or model in the calculator: NVIDIA DGX Spark · AMD Gorgon Halo 192GB
Every report on each card, with its source: NVIDIA DGX Spark · AMD Gorgon Halo 192GB