Report an Error

AMD Radeon PRO W6400

Graphics Processor
Navi 24
Cores
768
TMUs
48
ROPs
32
Memory Size
4 GB
Memory Type
GDDR6
Bus Width
64 bit
GPU Chip
GPU
I/O
I/O
Top
Top
Rear
Rear
Back
Back
The Radeon PRO W6400 is a professional graphics card by AMD, launched on January 19th, 2022. Built on the 6 nm process, and based on the Navi 24 graphics processor, in its Navi 24 XL-W variant, the card supports DirectX 12 Ultimate. The Navi 24 graphics processor is an average sized chip with a die area of 107 mm² and 5,400 million transistors. Unlike the fully unlocked Radeon RX 6500 XT, which uses the same GPU but has all 1024 shaders enabled, AMD has disabled some shading units on the Radeon PRO W6400 to reach the product's target shader count. It features 768 shading units, 48 texture mapping units, and 32 ROPs. The card also has 12 raytracing acceleration cores. AMD has paired 4 GB GDDR6 memory with the Radeon PRO W6400, which are connected using a 64-bit memory interface. The GPU is operating at a frequency of 2039 MHz, which can be boosted up to 2321 MHz, memory is running at 2000 MHz (16 Gbps effective).
Being a single-slot card, the AMD Radeon PRO W6400 does not require any additional power connector, its power draw is rated at 50 W maximum. Display outputs include: 2x DisplayPort 1.4a. Radeon PRO W6400 is connected to the rest of the system using a PCI-Express 4.0 x4 interface.

Graphics Processor

GPU Name
Navi 24
GPU Variant
Navi 24 XL-W
Architecture
RDNA 2.0
Foundry
TSMC
Process Size
6 nm
Transistors
5,400 million
Density
50.5M / mm²
Die Size
107 mm²

Graphics Card

Release Date
Jan 19th, 2022
Generation
Radeon Pro Navi
(Navi II Series)
Predecessor
Radeon Pro Vega
Production
Active
Bus Interface
PCIe 4.0 x4

Relative Performance

GeForce RTX 5090
1212%
GeForce RTX 4090
925%
GeForce RTX 5080
799%
GeForce RTX 4080 SUPER
713%
GeForce RTX 4080
707%
Radeon RX 7900 XTX
707%
GeForce RTX 5070 Ti
697%
Radeon RX 9070 XT
666%
Radeon RX 7900 XT
609%
GeForce RTX 3090 Ti
597%
GeForce RTX 4070 Ti SUPER
597%
Radeon RX 9070
596%
GeForce RTX 4070 Ti
546%
GeForce RTX 5070
541%
GeForce RTX 3090
533%
GeForce RTX 3080 Ti
526%
GeForce RTX 4070 SUPER
509%
Radeon RX 7900 GRE
501%
Radeon RX 6950 XT
493%
GeForce RTX 4070
486%
Radeon RX 6900 XT
481%
GeForce RTX 3080
474%
Radeon RX 7800 XT
472%
Radeon RX 6800 XT
456%
GeForce RTX 5060 Ti 16 GB
423%
GeForce RTX 5060 Ti 8 GB
420%
Radeon RX 7700 XT
414%
Radeon RX 9060 XT 16 GB
401%
GeForce RTX 3070 Ti
401%
Radeon RX 6800
387%
Radeon RX 9060 XT 8 GB
379%
GeForce RTX 3070
375%
GeForce RTX 2080 Ti
372%
GeForce RTX 4060 Ti 8 GB
370%
GeForce RTX 5060
364%
Radeon RX 6750 XT
355%
GeForce RTX 3060 Ti
328%
Radeon RX 6700 XT
322%
GeForce RTX 2080 SUPER
299%
Radeon RX 7600 XT
297%
GeForce RTX 4060
296%
Arc B580
295%
GeForce RTX 5050
288%
GeForce RTX 2080
286%
Radeon RX 6650 XT
279%
Radeon RX 7600
279%
GeForce RTX 2070 SUPER
266%
GeForce GTX 1080 Ti
263%
Arc A770
262%
GeForce RTX 3060 12 GB
253%
Radeon RX 6600 XT
249%
Radeon VII
249%
Arc A750
244%
Radeon RX 5700 XT
238%
GeForce RTX 2070
235%
Radeon RX 6600
224%
Arc A580
218%
GeForce RTX 2060 SUPER
217%
Radeon RX Vega 64
208%
GeForce RTX 2060
201%
Radeon RX 5700
201%
GeForce GTX 1080
197%
GeForce GTX 1070 Ti
193%
Radeon RX 5600 XT
191%
Radeon RX Vega 56
182%
GeForce GTX 1070
175%
GeForce GTX 1660 SUPER
166%
GeForce GTX 1660 Ti
166%
GeForce GTX 980 Ti
157%
GeForce RTX 3050 8 GB
156%
Radeon R9 FURY X
154%
GeForce GTX 1660
153%
Radeon RX 590
144%
Radeon R9 FURY
140%
GeForce GTX 980
139%
GeForce GTX 1650 SUPER
137%
Radeon RX 6500 XT
136%
Radeon RX 5500 XT
134%
Radeon RX 580
133%
GeForce GTX 1060 6 GB
130%
Radeon R9 390X
128%
GeForce GTX 690
127%
Radeon RX 480
126%
Radeon HD 7990
125%
GeForce GTX 780 Ti
123%
GeForce GTX 970
119%
Radeon R9 290X
119%
Radeon R9 390
117%
Radeon RX 570
116%
Radeon R9 290
110%
Radeon RX 470
108%
GeForce GTX 1650
102%
Radeon RX 6400
100%
Radeon PRO W6400
100%
Arc A380
99%
GeForce GTX 780
99%
Radeon HD 7970 GHz Edition
89%
GeForce GTX 590
89%
Radeon R9 280X
88%
Radeon HD 6990
86%
GeForce GTX 1050 Ti
81%
GeForce GTX 680
80%
Radeon R9 380
79%
Radeon HD 7970
79%
GeForce GTX 770
79%
Radeon R9 285
78%
GeForce GTX 960
76%
GeForce GTX 670
74%
Radeon HD 5970
67%
GeForce GTX 1630
67%
Radeon HD 7950
65%
GeForce GTX 1050
65%
GeForce GTX 760
65%
GeForce GTX 580
65%
GeForce GTX 660 Ti
64%
Radeon R9 270X
64%
Radeon HD 7870 GHz Edition
62%
GeForce GTX 950
62%
Radeon RX 560
58%
GeForce GTX 570
57%
GeForce GTX 660
57%
Radeon RX 460
57%
Radeon R7 370
57%
Radeon HD 6970
55%
GeForce GTX 480
52%
Radeon HD 7850
51%
GeForce GTX 295
50%
Radeon HD 6950
49%
GeForce GTX 750 Ti
48%
Radeon HD 4870 X2
48%
GeForce GTX 560 Ti
47%
Radeon HD 5870
46%
Radeon HD 6870
43%
GeForce GTX 470
42%
GeForce GTX 650 Ti
40%
Radeon HD 5850
39%
GeForce GTX 285
36%
Radeon HD 6850
36%
GeForce GTX 280
33%
Radeon HD 7770 GHz Edition
33%
GeForce GTX 275
33%
GeForce GT 1030
33%
GeForce GTX 460
32%
Radeon HD 4890
31%
Radeon HD 6790
31%
Radeon HD 5830
29%
GeForce GTX 650
28%
GeForce GTX 550 Ti
27%
Radeon HD 4870
27%
GeForce GTX 260
27%
Radeon HD 5770
26%
Radeon HD 7750
26%
Radeon HD 5750
23%
GeForce GTS 450
22%
GeForce GTS 250
21%
Radeon HD 4850
21%
Radeon HD 4770
20%
Radeon HD 4830
19%
Radeon HD 6670
18%
GeForce 9800 GT
17%
GeForce GT 640
17%
Radeon HD 5670
16%
GeForce 9600 GT
15%
GeForce GT 240
13%
GeForce GT 440
13%
Radeon HD 4670
12%
Radeon HD 5570
11%
GeForce GT 430
11%
GeForce GT 220
8%
GeForce GT 520
7%
Radeon HD 6450
6%
Radeon HD 5450
5%
Radeon HD 4550
4%
GeForce 9400 GT
3%
GeForce 210
3%
Based on TPU review data: "Performance Summary" at 1920x1080, 4K for RTX 3080 and faster.
Performance estimated based on architecture, shader count and clocks.

Clock Speeds

Base Clock
2039 MHz
Boost Clock
2321 MHz
Memory Clock
2000 MHz
16 Gbps effective

Memory

Memory Size
4 GB
Memory Type
GDDR6
Memory Bus
64 bit
Bandwidth
128.0 GB/s

Render Config

Shading Units
768
TMUs
48
ROPs
32
Compute Units
12
RT Cores
12
L0 Cache
32 KB per WGP
L1 Cache
128 KB per Array
L2 Cache
1024 KB
L3 Cache
8 MB

Theoretical Performance

Pixel Rate
74.27 GPixel/s
Texture Rate
111.4 GTexel/s
FP16 (half)
7.130 TFLOPS (2:1)
FP32 (float)
3.565 TFLOPS
FP64 (double)
222.8 GFLOPS (1:16)

Board Design

Slot Width
Single-slot
TDP
50 W
Suggested PSU
250 W
Outputs
2x DisplayPort 1.4a
Power Connectors
None
Board Number
D637

Graphics Features

DirectX
12 Ultimate (12_2)
OpenGL
4.6
OpenCL
2.2
Vulkan
1.3
Shader Model
6.8

Navi 24 GPU Notes

Generation: Navi II
Codename: Beige Goby
Ray Tracing Cores: 1st Gen
Infinity Cache: 1st Gen
Graphics/Compute: 10.3.5
Shader ISA: GFX10.3 (gfx1034)
Display Core Next: 3.0.3
Video Core Next: 3.0.33
System DMA: 5.2.5
Platform Security Processor: 11.0.13

Per SIMD32:
- 10 KB Scalar Register File

Per CU:
- 16 KB Vector Data Cache
- 64 KB Local Data Share (GCN-Mode)

Per WGP:
- 16 KB Scalar Data Cache / K Cache
- 32 KB Instruction Cache
- 128 KB Local Data Share

Latest Drivers:
Windows 7:
64-bit: AMD Software: Adrenalin Edition 22.6.1

Windows 10 / 11:
64-bit: AMD Software: Adrenalin Edition: Latest
64-bit: AMD Software: PRO Edition 22.Q4
Sep 18th, 2025 08:56 CEST change timezone

New Forum Posts

Popular Reviews

TPU on YouTube

Controversial News Posts