GPU Models for LLM Inference — Specs, VRAM & Prices
Browse and compare GPU hardware for LLM inference
GeForce RTX 3090 Ti
NVIDIA · Ampere
VRAM
24 GB
Memory BW
1,008 GB/s
FP16
160 TFLOPS
MSRP
USD 1,999.00
GeForce GTX 1650
NVIDIA · Turing
VRAM
4 GB
Memory BW
192 GB/s
FP16
— TFLOPS
MSRP
USD 149.00
AMD Radeon RX 6500 XT
AMD · RDNA2
VRAM
4 GB
Memory BW
144 GB/s
FP16
11.53 TFLOPS
MSRP
USD 199.00
Apple M1 Max
Apple · M1
VRAM
32 GB
Memory BW
400 GB/s
FP16
20.8 TFLOPS
MSRP
USD 1,999.00
Intel Arc A580
Intel · Alchemist
VRAM
8 GB
Memory BW
512 GB/s
FP16
83.7 TFLOPS
MSRP
USD 179.00
Intel Iris Xe Graphics (96 EU)
Intel · Xe-LP
VRAM
0 GB
Memory BW
68 GB/s
FP16
— TFLOPS
MSRP
—
GeForce RTX 5060 Ti
NVIDIA · Blackwell
VRAM
16 GB
Memory BW
448 GB/s
FP16
94.9 TFLOPS
MSRP
USD 429.00
Apple M1 Ultra
Apple · M1
VRAM
64 GB
Memory BW
800 GB/s
FP16
42 TFLOPS
MSRP
USD 3,999.00
GeForce RTX 4090
NVIDIA · Ada Lovelace
VRAM
24 GB
Memory BW
1,008 GB/s
FP16
330.3 TFLOPS
MSRP
USD 1,599.00