Radeon Instinct MI350X vs RX 6400

Primary details

GPU architecture, market segment, value for money and other general parameters compared.

Place in the ranking	336	not rated
Place by popularity	not in top-100	not in top-100
Cost-effectiveness evaluation	40.11	no data
Power efficiency	27.18	no data
Architecture	RDNA 2.0 (2020−2025)	CDNA 4.0 (2025−2026)
GPU code name	Navi 24	MI350 256CU
Market segment	Desktop	Workstation
Release date	19 January 2022 (4 years ago)	12 June 2025 (1 year ago)
Launch price (MSRP)	$159	no data

Cost-effectiveness evaluation

The higher the ratio, the better. We use the manufacturer's recommended prices.

Performance to price scatter graph

Currently popular graphics cards are shown for comparison.

Detailed specifications

General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Real power consumption of some graphics cards can well exceed their nominal TDP, especially if overclocked.

Pipelines / CUDA cores	768	16384
Core clock speed	1923 MHz	1000 MHz
Boost clock speed	2321 MHz	2200 MHz
Number of transistors	5,400 million	185,000 million
Manufacturing process technology	6 nm	3 nm
Power consumption (TDP)	53 Watt	1000 Watt
Texture fill rate	111.4	2,252.8
Floating-point processing power	3.565 TFLOPS	72.09 TFLOPS
ROPs	32	no data
TMUs	48	1024
Tensor Cores	no data	1024
Ray Tracing Cores	12	no data
L0 Cache	192 KB	no data
L1 Cache	256 KB	4 MB
L2 Cache	1024 KB	16 MB
L3 Cache	16 MB	256 MB

Form factor & compatibility

Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).

Interface	PCIe 4.0 x4	PCIe 5.0 x16
Length	no data	102 mm
Width	1-slot	OAM Module
Supplementary power connectors	None	None

VRAM capacity and type

Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.

Memory type	GDDR6	HBM3e
Maximum RAM amount	4 GB	288 GB
Memory bus width	64 Bit	8192 Bit
Memory clock speed	2000 MHz	2000 MHz
Memory bandwidth	128.0 GB/s	8.19 TB/s
Resizable BAR	+	+

Connectivity and outputs

This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.

Display Connectors	1x HDMI 2.1, 1x DisplayPort 1.4a	No outputs
HDMI	+	-

API and SDK support

List of supported 3D and general-purpose computing APIs, including their specific versions.

DirectX	12 Ultimate (12_2)	N/A
Shader Model	6.7	N/A
OpenGL	4.6	N/A
OpenCL	2.2	3.0
Vulkan	1.3	N/A
DLSS	-	+

Pros & cons summary

---

Recency	19 January 2022	12 June 2025
Maximum RAM amount	4 GB	288 GB
Chip lithography	6 nm	3 nm
Power consumption (TDP)	53 Watt	1000 Watt