llamaperf

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).

NVIDIA DGX Spark
Memory
128GB unified
Memory bandwidth
273 GB/s
FP16 compute
125 TFLOPS
Reports
99
AMD Gorgon Halo 192GB
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

ModelNVIDIA DGX SparkAMD Gorgon Halo 192GB
gpt-oss 117B · 5.1B active4-bit52.9one runPP 1689.5 (one run)llama.cppcontext not stated49.02 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.

ModelNVIDIA DGX SparkAMD Gorgon Halo 192GB
gpt-oss 117B · 5.1B active18.0 t/sQ6_K11.7 t/sQ8_0
Qwen3.8 27B4.0 t/sFP162.8 t/sFP16
Qwen3.8 125B · 6B active14.4 t/sQ6_K9.5 t/sQ8_0
Qwen3.6 35B · 3B active14.5 t/sFP1610.0 t/sFP16
DeepSeek V4 Flash 284B · 13B active38.3 t/sQ2_K12.5 t/sQ4_K_M
DeepSeek V4.1 Flash 552B · 16B activedoesn't fit at these settings16.7 t/sQ2_K
Qwen3.6 27B4.0 t/sFP162.8 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

More comparisons