GPU Models for LLM Inference — Specs, VRAM & Prices
Browse and compare GPU hardware for LLM inference
AMD Radeon RX 7900 XT
AMD · RDNA3
VRAM
20 GB
Memory BW
800 GB/s
FP16
51.61 TFLOPS
MSRP
USD 899.00
AMD Radeon RX 7700
AMD · RDNA3
VRAM
16 GB
Memory BW
624 GB/s
FP16
25.2 TFLOPS
MSRP
USD 449.00
AMD Radeon RX 6650 XT
AMD · RDNA2
VRAM
8 GB
Memory BW
280 GB/s
FP16
21.59 TFLOPS
MSRP
USD 399.00
GeForce GTX 1650 GDDR6
NVIDIA · Turing
VRAM
4 GB
Memory BW
192 GB/s
FP16
— TFLOPS
MSRP
USD 149.00
AMD Radeon RX 6950 XT
AMD · RDNA2
VRAM
16 GB
Memory BW
576 GB/s
FP16
47.31 TFLOPS
MSRP
USD 1,099.00
Intel Arc A750
Intel · Alchemist
VRAM
8 GB
Memory BW
512 GB/s
FP16
117.5 TFLOPS
MSRP
USD 289.00
Intel Arc Graphics 140V
Intel · Xe2-LPG
VRAM
0 GB
Memory BW
136.5 GB/s
FP16
32 TFLOPS
MSRP
—
Intel Arc A310
Intel · Alchemist
VRAM
4 GB
Memory BW
124 GB/s
FP16
24.6 TFLOPS
MSRP
USD 99.00
Intel Arc A770 8GB
Intel · Alchemist
VRAM
8 GB
Memory BW
512 GB/s
FP16
137.6 TFLOPS
MSRP
USD 329.00
Intel Arc B580
Intel · Battlemage
VRAM
12 GB
Memory BW
456 GB/s
FP16
109.4 TFLOPS
MSRP
USD 249.00
Apple M4 Max
Apple · M4
VRAM
36 GB
Memory BW
546 GB/s
FP16
36.8 TFLOPS
MSRP
USD 1,999.00
Intel Arc B570
Intel · Battlemage
VRAM
10 GB
Memory BW
380 GB/s
FP16
92.2 TFLOPS
MSRP
USD 219.00
Apple M3 Pro
Apple · M3
VRAM
18 GB
Memory BW
150 GB/s
FP16
14.8 TFLOPS
MSRP
USD 1,999.00
Intel Arc A770 16GB
Intel · Alchemist
VRAM
16 GB
Memory BW
560 GB/s
FP16
137.6 TFLOPS
MSRP
USD 349.00
Intel Arc A380
Intel · Alchemist
VRAM
6 GB
Memory BW
186 GB/s
FP16
32.8 TFLOPS
MSRP
USD 139.00
Apple M3 Max
Apple · M3
VRAM
36 GB
Memory BW
400 GB/s
FP16
28.2 TFLOPS
MSRP
USD 3,199.00
AMD Radeon RX 7600 XT
AMD · RDNA3
VRAM
16 GB
Memory BW
288 GB/s
FP16
22.57 TFLOPS
MSRP
USD 329.00
GeForce RTX 4070
NVIDIA · Ada Lovelace
VRAM
12 GB
Memory BW
504 GB/s
FP16
116.8 TFLOPS
MSRP
USD 599.00