FR
Comparator

L40S 48 GB vs Mac Studio M4 Max 128 GB

Up to three cards or machines side by side, with the expected speed on the model of your choice. The best of each row is highlighted.

RTX 5090 vs RTX 4090NVIDIA DGX Spark vs RTX 5090RTX 3090 vs RTX 4090Mac Studio M4 Max vs NVIDIA DGX SparkMini-PC Ryzen AI Max+ 395 vs NVIDIA DGX SparkH100 vs H200RTX PRO 6000 Blackwell vs RTX 6000 AdaRadeon RX 7900 XTX vs RTX 4090
L40S 48 GBMac Studio M4 Max 128 GB
Usable memory48 GB
96 GB
Bandwidth864 GB/s
546 GB/s
FP16 compute~362 TF
~34 TF
Power350 W
150 W
Indicative price€7,500
€4,400
Complete machine€13,500
€4,400
€ per usable GB€281
€46
Qwen3 32B (Q4_K_M)~24 tok/s
~15 tok/s
€ per tok/s on Qwen3 32B€563
€291
Biggest model alone (Q4)Llama 3.3 70B
Mistral Large 123B

For Qwen3 32B: the fastest is L40S 48 GB (~24 tok/s), the best speed for the price is Mac Studio M4 Max 128 GB.

Can I run it?

Pick a model and your hardware: instant verdict, and the cheapest alternatives if it doesn’t fit.

Yes, but it’s tight
47.4 GB needed48 GB available
Speed~18 tok/s
Occupancy99 %
Machine€2,400

Other options

Mini-PC Ryzen AI Max+ 395 128 GB~3.3 tok/s€2,300
NVIDIA DGX Spark 128 GB~3.5 tok/s€4,000
Mac Studio M4 Max 128 GB~7.1 tok/s€4,400
4 × RTX 4060 Ti 16 GB~11 tok/s€4,600
4 × Radeon RX 7800 XT 16 GB~24 tok/s€4,800