llamaperf

NVIDIA DGX Spark vs M2 Max 64GB for local LLMs

99 reports on the NVIDIA DGX Spark and 20 on the M2 Max 64GB

Which is faster for local LLMs?

On Gemma 4 26B · 4B active at 4-bit, the NVIDIA DGX Spark has 59.1 generation tokens/s (2 runs); prompt processing 2657.0 tokens/s (one run); the M2 Max 64GB has 61.6 generation tokens/s (one run); prompt processing 465.2 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 1.5x higher on the M2 Max 64GB (273 GB/s on the NVIDIA DGX Spark, 410 on the M2 Max 64GB). Across 2 shared models with generation measurements on both cards, the NVIDIA DGX Spark's median is higher on 1 and the M2 Max 64GB's on 1.

NVIDIA DGX Spark
Memory
128GB unified
Memory bandwidth
273 GB/s
FP16 compute
125 TFLOPS
Reports
99
M2 Max 64GB
Memory
64GB unified
Memory bandwidth
410 GB/s
FP16 compute
13.6 TFLOPS
Reports
20

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 SparkM2 Max 64GB
Gemma 4 26B · 4B active4-bit59.12 runsPP 2657.0 (one run)llama.cpp, vLLM256K context, 1 not stated61.6one runPP 465.2 (one run)MLXcontext not stated
Qwen3.6 35B · 3B active4-bit78.3one runPP 3556.7 (one run)llama.cpp, vLLM128K context, 1 not stated77.52 runsLM Studio, Ollama32K to 256K 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.

ModelNVIDIA DGX SparkM2 Max 64GB
Gemma 4 26B · 4B active10.8 t/sFP1628.2 t/sQ8_0
Qwen3.6 35B · 3B active14.5 t/sFP1632.9 t/sQ8_0
Qwen3.8 27B4.0 t/sFP1610.4 t/sQ8_0
Qwen3.8 125B · 6B active14.4 t/sQ6_K47.5 t/sQ2_K
DeepSeek V4 Flash 284B · 13B active38.3 t/sQ2_Kdoesn't fit at these settings
DeepSeek V4.1 Flash 552B · 16B activedoesn't fit at these settingsdoesn't fit at these settings
Qwen3.6 27B4.0 t/sFP1610.4 t/sQ8_0
GLM-5.3 320B · 18B active12.7 t/sQ2_Kdoesn't fit at these settings

Change the context, RAM or model in the calculator: NVIDIA DGX Spark · M2 Max 64GB

Every report on each card, with its source: NVIDIA DGX Spark · M2 Max 64GB

More comparisons