llamaperf

NVIDIA B200 180GB vs NVIDIA DGX Spark for local LLMs

1 report on the NVIDIA B200 180GB and 99 on the NVIDIA DGX Spark

Which is faster for local LLMs?

Nobody has reported the same model at the same quant on both cards yet, so there's no measured head-to-head. Memory bandwidth, which caps how fast a card can write, is 29.3x higher on the NVIDIA B200 180GB (8,000 GB/s on the NVIDIA B200 180GB, 273 on the NVIDIA DGX Spark). The estimates below compare them on the models people run most.

NVIDIA B200 180GB
Memory
180GB
Memory bandwidth
8,000 GB/s
FP16 compute
2250 TFLOPS
Reports
1
NVIDIA DGX Spark
Memory
128GB unified
Memory bandwidth
273 GB/s
FP16 compute
125 TFLOPS
Reports
99

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.

ModelNVIDIA B200 180GBNVIDIA DGX Spark
Qwen3.8 27B81.5 t/sFP164.0 t/sFP16
Qwen3.8 125B · 6B active266.2 t/sQ8_014.4 t/sQ6_K
Qwen3.6 35B · 3B active293.3 t/sFP1614.5 t/sFP16
DeepSeek V4 Flash 284B · 13B active435.6 t/sQ4_K_S38.3 t/sQ2_K
DeepSeek V4.1 Flash 552B · 16B active449.5 t/sQ2_Kdoesn't fit at these settings
Qwen3.6 27B81.5 t/sFP164.0 t/sFP16

Change the context, RAM or model in the calculator: NVIDIA B200 180GB · NVIDIA DGX Spark

Every report on each card, with its source: NVIDIA B200 180GB · NVIDIA DGX Spark

More comparisons