AMD Instinct MI350X vs AMD Instinct MI300A Full Specs

Summary

16,384 Shaders 2.2GHz	14,592 Shaders 2.1GHz
288GB HBM3e8TB/s	128GB HBM35.33TB/s
Peak·FP32·FP16 144.2 TFLOPS	Peak·FP32·FP16 122.6 TFLOPS
Form Factor OAM Module	Form Factor APU SH5 Socket
TDP 1000W	TDP 560W

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP4 FP4 Tensor Sparse Tensor FP8-16 FP8-16 Tensor Sparse Tensor FP8-32 FP8-32 Tensor Sparse Tensor FP16-16 FP16-16 Tensor Sparse Tensor FP16-32 FP16-32 Tensor Sparse Tensor FP32 FP64 Tensor FP64 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth TDP

Instinct MI350X18.45 PFLOPSFP4 Tensor Sparse

x4.71

Instinct MI300A3.92 POPSINT4 Tensor Sparse

x1

Show Top Score

Theoretical Performance

Clock Speed2200MHz UC·Boost·OC	Clock Speed2100MHz UC·Base·Boost·OC
Peak OPS 18.45 PFLOPSFP4 Tensor Sparse	Peak OPS 3.92 POPSINT4 Tensor Sparse
Tensor FP4 9.23 PFLOPS FP4 Tensor Sparse 18.45 PFLOPS	-
Tensor FP8-16 4.61 PFLOPS FP8-16 Tensor Sparse 9.23 PFLOPS Tensor FP8-32 4.61 PFLOPS FP8-32 Tensor Sparse 9.23 PFLOPS	Tensor FP8-16 1.96 PFLOPS FP8-16 Tensor Sparse 3.92 PFLOPS Tensor FP8-32 1.96 PFLOPS FP8-32 Tensor Sparse 3.92 PFLOPS
Tensor FP16-16 2.31 PFLOPS FP16-16 Tensor Sparse 4.61 PFLOPS Tensor FP16-32 2.31 PFLOPS FP16-32 Tensor Sparse 4.61 PFLOPS	Tensor FP16-16 980.6 TFLOPS FP16-16 Tensor Sparse 1.96 PFLOPS Tensor FP16-32 980.6 TFLOPS FP16-32 Tensor Sparse 1.96 PFLOPS
Tensor BF16 2.31 PFLOPS BF16 Tensor Sparse 4.61 PFLOPS	Tensor BF16 980.6 TFLOPS BF16 Tensor Sparse 1.96 PFLOPS
Tensor TF32 -	Tensor TF32 490.3 TFLOPS
FP32 144.2 TFLOPS Tensor FP32 144.2 TFLOPS	FP32 122.6 TFLOPS Tensor FP32 122.6 TFLOPS
FP64 72.09 TFLOPS Tensor FP64 72.09 TFLOPS	FP64 61.29 TFLOPS Tensor FP64 122.6 TFLOPS
Tensor INT4 4.61 POPS	Tensor INT4 1.96 POPS
Tensor INT8 4.61 POPS	Tensor INT8 1.96 POPS
Texture Rate -	Texture Rate 1.92 TTexel/s

Core Config

Shaders 16,384 Shaders	Shaders 14,592 Shaders
TMUs -	TMUs 912 TMUs
Tensor Cores 1,024 T-Cores	Tensor Cores 912 T-Cores
CUs 256 CUs	CUs 228 CUs

Clocks

Base Clock -	Base Clock 1GHz
Boost Clock 2.2GHz	Boost Clock 2.1GHz

Cache

L2 Cache 16.4MB shared	L2 Cache 16.4MB shared
L3 Cache 256MB shared	L3 Cache 192MB shared

Memory

288GB HBM3e	128GB HBM3
Memory Bus 8192-bit	Memory Bus 8192-bit
Memory Speed 7.8GT/s	Memory Speed 5.2GT/s
Memory Bandwidth 8TB/s	Memory Bandwidth 5.33TB/s
ECC Yes	ECC Yes

Power & Thermals

TDP 1000W

TDP 560W

Encoder

Encoder Model 4x VCN 4.0

Encoder Model 2x VCN 2.6

Decoder

Decoder Model 4x VCN 4.0

Decoder Model 2x VCN 2.6

Card

Form Factor OAM Module	Form Factor APU SH5 Socket
Cooling Passive	Cooling Passive

Chip

Manufacturer AMD	Manufacturer AMD
Chip Designer AMD	Chip Designer AMD
Architecture CDNA 4	Architecture CDNA 3
Family Instinct	Family Instinct
Branding	Branding
Codename CDNA Next	Codename Aqua Vanjaram
Chip Variant -	Chip Variant Aqua Vanjaram XT
Market Segment Server	Market Segment Server
Release Date Jun 12, 2025	Release Date Dec 6, 2023

Fabrication

Foundry TSMC	Foundry TSMC
Other Foundries - TSMCIO	Other Foundries TSMCActive Interposer -
Fabrication Node N3P - N6IO	Fabrication Node N5 N6Active Interposer -
Die Size 1448mm²	Die Size 1110mm²
Transistor Count 139.2 Billion 46 BillionIO	Transistor Count 109.5 Billion -
Transistor Density 96.13 MTr/mm²	Transistor Density 98.65 MTr/mm²

Images

No images available

No images available

Competitors

AMDInstinct MI350X vs GPU AMDInstinct MI355X AMDInstinct MI350X vs GPU AMDInstinct MI325X AMDInstinct MI350X vs GPU AMDInstinct MI300X Show 12 more

AMDInstinct MI300A vs GPU AMDInstinct MI300X AMDInstinct MI300A vs GPU AMDInstinct MI250X AMDInstinct MI300A vs GPU AMDInstinct MI325X Show 12 more