GPU Models for LLM Inference — Specs, VRAM & Prices
Browse and compare GPU hardware for LLM inference
Apple M2 Max
Apple · M2
VRAM
32 GB
Memory BW
400 GB/s
FP16
27.2 TFLOPS
MSRP
USD 1,999.00
GeForce GTX 1630
NVIDIA · Turing
VRAM
4 GB
Memory BW
96 GB/s
FP16
— TFLOPS
MSRP
USD 169.00
AMD Radeon RX 9070 XT
AMD · RDNA4
VRAM
16 GB
Memory BW
640 GB/s
FP16
48.7 TFLOPS
MSRP
USD 599.00
AMD Radeon RX 7600
AMD · RDNA3
VRAM
8 GB
Memory BW
288 GB/s
FP16
21.75 TFLOPS
MSRP
USD 269.00
AMD Radeon RX 7900 GRE
AMD · RDNA3
VRAM
16 GB
Memory BW
576 GB/s
FP16
45.98 TFLOPS
MSRP
USD 549.00
AMD Radeon RX 9050
AMD · RDNA4
VRAM
8 GB
Memory BW
288 GB/s
FP16
10.6 TFLOPS
MSRP
USD 279.00
Apple M2 Pro
Apple · M2
VRAM
16 GB
Memory BW
200 GB/s
FP16
13.6 TFLOPS
MSRP
USD 1,299.00
AMD Radeon RX 6900 XT
AMD · RDNA2
VRAM
16 GB
Memory BW
512 GB/s
FP16
46.08 TFLOPS
MSRP
USD 999.00
AMD Radeon RX 6600 XT
AMD · RDNA2
VRAM
8 GB
Memory BW
256 GB/s
FP16
21.21 TFLOPS
MSRP
USD 379.00
AMD Radeon RX 9060 XT 16GB
AMD · RDNA4
VRAM
16 GB
Memory BW
320 GB/s
FP16
25.6 TFLOPS
MSRP
USD 349.00
AMD Radeon RX 9070 GRE
AMD · RDNA4
VRAM
12 GB
Memory BW
432 GB/s
FP16
34.3 TFLOPS
MSRP
USD 549.00
AMD Radeon RX 9070
AMD · RDNA4
VRAM
16 GB
Memory BW
640 GB/s
FP16
36.1 TFLOPS
MSRP
USD 549.00
Apple M1 Pro
Apple · M1
VRAM
16 GB
Memory BW
200 GB/s
FP16
10.6 TFLOPS
MSRP
USD 1,999.00
AMD Radeon RX 6750 XT
AMD · RDNA2
VRAM
12 GB
Memory BW
432 GB/s
FP16
26.62 TFLOPS
MSRP
USD 549.00
AMD Radeon RX 7800 XT
AMD · RDNA3
VRAM
16 GB
Memory BW
624 GB/s
FP16
37.32 TFLOPS
MSRP
USD 499.00
AMD Radeon RX 6700 XT
AMD · RDNA2
VRAM
12 GB
Memory BW
384 GB/s
FP16
26.43 TFLOPS
MSRP
USD 479.00
AMD Radeon RX 6800
AMD · RDNA2
VRAM
16 GB
Memory BW
512 GB/s
FP16
32.33 TFLOPS
MSRP
USD 579.00
AMD Radeon RX 9060 XT 8GB
AMD · RDNA4
VRAM
8 GB
Memory BW
320 GB/s
FP16
25.6 TFLOPS
MSRP
USD 299.00
AMD Radeon RX 7400
AMD · RDNA3
VRAM
8 GB
Memory BW
173 GB/s
FP16
15.77 TFLOPS
MSRP
USD 159.00