Radeon Instinct MI350X vs Pro W6600

Primary details

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

Place in the ranking	156	not rated
Place by popularity	not in top-100	not in top-100
Cost-effectiveness evaluation	25.70	no data
Power efficiency	27.57	no data
Architecture	RDNA 2.0 (2020−2025)	CDNA 4.0 (2025)
GPU code name	Navi 23	CDNA Next
Market segment	Workstation	Workstation
Release date	8 June 2021 (4 years ago)	2025 (1 year ago)
Launch price (MSRP)	$649	no data

Cost-effectiveness evaluation

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

Performance to price scatter graph

Detailed specifications

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

Pipelines / CUDA cores	1792	16384
Core clock speed	2331 MHz	1000 MHz
Boost clock speed	2903 MHz	2200 MHz
Number of transistors	11,060 million	185,000 million
Manufacturing process technology	7 nm	3 nm
Power consumption (TDP)	100 Watt	1000 Watt
Texture fill rate	325.1	2,252.8
Floating-point processing power	10.4 TFLOPS	72.09 TFLOPS
ROPs	64	no data
TMUs	112	1024
Tensor Cores	no data	1024
Ray Tracing Cores	28	no data
L0 Cache	448 KB	no data
L1 Cache	512 KB	4 MB
L2 Cache	2 MB	16 MB
L3 Cache	32 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 x16	PCIe 5.0 x16
Length	241 mm	no data
Width	1-slot	OAM Module
Supplementary power connectors	1x 6-pin	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	8 GB	288 GB
Memory bus width	128 Bit	8192 Bit
Memory clock speed	1750 MHz	2000 MHz
Memory bandwidth	224.0 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

4x DisplayPort

No outputs

API and SDK support

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

DirectX	12.0 Ultimate (12_2)	N/A
Shader Model	6.5	N/A
OpenGL	4.6	N/A
OpenCL	2.1	3.0
Vulkan	1.2	N/A
DLSS	-	+

Pros & cons summary

---

Maximum RAM amount	8 GB	288 GB
Chip lithography	7 nm	3 nm
Power consumption (TDP)	100 Watt	1000 Watt