AMD's own product name for this card is 'AMD Radeon PRO W7800 48GB'. It is stored here as the 48GB variant of the W7800 rather than as a separate model, because it is the same 70 compute unit bin at the same 260 W with the same precision ladder; only the memory system changes, to a 384-bit bus at 864 GB/s with 96 MB of Infinity Cache. AMD issued no press release for it, so its year rests on driver release notes (see data_source).

AMD Radeon PRO W7800 48GB

RDNA 3 PCIe 2024 5nm Spec confidence: Official
FP32
45
TFLOPS
VRAM
48 GB
GDDR6
Bandwidth
864 GB/s
memory
TDP
260 W
173.8 TFLOPS/kW
Download datasheet

Overview

The 48 GB Radeon PRO W7800 takes the 70 compute unit W7800 bin and gives it the W7900's memory system: 48 GB of ECC GDDR6 on a 384-bit bus at 864 GB/s, with 96 MB of Infinity Cache. Compute is unchanged from the 32 GB card at 45.2 TFLOPS of FP32 vector and 90.4 TFLOPS of FP16 matrix, and so is the 260 W board power, so the whole value of the SKU is capacity and bandwidth for models that will not fit in 32 GB. It stays a double-slot card, which makes multi-GPU builds practical. RDNA 3 offers no FP8 and no structured sparsity, and AMD publishes no FP64 or BF16 rate.

Performance

Peak theoretical throughput by precision type

PrecisionPeak
FP64
No verified data available
FP32
32-bit floating point
45TFLOPS
TF32
No verified data available
BF16
No verified data available
FP16
16-bit floating point
90TFLOPS
FP8
No verified data available
FP6
No verified data available
FP4
No verified data available
INT8
8-bit integer
90TOPS
INT4
4-bit integer
181TOPS

Every figure here is dense. The vendor documents no structured (2:4) sparsity mode for this part, so there is no second number to quote.

The Radeon PRO W7800 48GB in the GPU landscape

Peak FP16 TFLOPS (dense) against TDP, single-GPU parts tracked by Flopper

06001,2001,8002,4003,0000 W250 W500 W750 W1000 W1250 W1500 WInstinct MI355XRadeon PRO W7800 48GB

Higher and further left is better: more half-precision throughput for less power.

Specifications

Architecture

RDNA 3

Form Factor

PCIe

Launch Year

2024

Process Node

5nm

Memory

48 GB GDDR6

Bandwidth

864 GB/s

TDP

260 W

Max Power

260 W

Transistors

57.7 billion

Stream Processors

4,480

Spec Confidence

Official

Full Specifications

Compute Engine
Stream Processors 4,480
Tensor Cores 140 (RDNA 3)
Compute Units 70
Chip Design
Transistors 57.7 billion
Process Node 5nm
Memory
VRAM 48 GB
Memory Type GDDR6
Bandwidth 864 GB/s
Interface Width 384-bit
Interconnect & I/O
PCIe Gen 4 x16
Cache
Infinity Cache 96 MB
Power & Thermal
TDP 260 W
Max Board Power 260 W
Power Connector 2x8-Pin
Cooling Active
Enterprise Features
ECC Memory Yes
Sparsity No
Compute APIs ROCm, OpenCL, HIP
Physical & Media
Width 2-slot
General
Form Factor PCIe
Architecture RDNA 3
Process Node 5nm
Launch Year 2024

Datasheet & Resources

Data Provenance

Every figure traced to a source

Primary Source

Publisher
AMD
Published
No verified data available

Data Quality

Spec confidence
Official
Clock basis
Boost
Core precisions with figures
3 of 9
Normalization
All values in TFLOPS

Compare cloud providers offering on-demand GPU instances for AI training, inference, and HPC workloads.

Browse GPU Cloud Providers

Similar GPUs

Frequently Asked Questions

How many TFLOPS does the AMD Radeon PRO W7800 have?

The AMD Radeon PRO W7800 delivers 45 TFLOPS FP32 and 90 TFLOPS FP16 at peak. Flopper does not currently have a verified FP8 throughput figure for it.

What is the power consumption of the AMD Radeon PRO W7800?

The AMD Radeon PRO W7800 has a TDP (Thermal Design Power) rating of 260 watts.

How much memory does the AMD Radeon PRO W7800 have?

The AMD Radeon PRO W7800 is equipped with 48 GB of VRAM with 864 GB/s of memory bandwidth.

What architecture is the AMD Radeon PRO W7800 based on?

The AMD Radeon PRO W7800 is based on the RDNA 3 architecture, launched in 2024.

Stay Updated on GPU Releases

Get notified when new GPUs are added or specifications are updated.

Loading verification...

No spam, unsubscribe anytime.

Back to GPUs