Apple publishes no throughput figures for M-series silicon. Its technical specification pages give GPU core counts, Neural Engine core counts and memory bandwidth, and no FLOPS of any kind, while its newsroom compares generations only in relative terms. The FP32 figure shown here is the one Apple quoted for some M1 and M2 family chips and is otherwise third-party, so it is recorded as a claim rather than a specification. No FP16 or INT8 figure is listed: Apple publishes neither, and an INT8 rate derived from GPU FP32 would in any case describe the Neural Engine, which is a separate unit Apple rates in TOPS.

Apple M1 Ultra

Type: APUArchitecture: Apple M1Form factor: SoCReleased: 2022Process: 5nmSpec confidence: Vendor claimed
FP32
21
TFLOPS
Memory
128 GB
LPDDR5
Bandwidth
800 GB/s
memory

Performance

Peak theoretical throughput by precision type

PrecisionPeak
FP64
No verified data available
FP32
32-bit floating point
21TFLOPS
TF32
No verified data available
BF16
No verified data available
FP16
No verified data available
FP8
No verified data available
FP6
No verified data available
FP4
No verified data available
INT8
No verified data available

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.

Specifications

Architecture

Apple M1

Form Factor

SoC

Launch Year

2022

Process Node

5nm

Memory

128 GB LPDDR5

Bandwidth

800 GB/s

TDP

No verified data available

Max power

No verified data available

Spec Confidence

Vendor claimed

Full Specifications

Memory
Memory 128 GB
Memory Type LPDDR5
Bandwidth 800 GB/s
Interface Width 1024-bit
Power & Thermal
TDP No verified data available
Max power No verified data available
Enterprise Features
Sparsity No
General
Form Factor SoC
Architecture Apple M1
Process Node 5nm
Launch Year 2022

Datasheet & Resources

Flopper Datasheet

Apple M1 Ultra specifications, generated from our database. Printable.

Apple unveils M1 Ultra, the world's most powerful chip for a personal computer

Apple · 2022-03-08

View

Data Provenance

Every figure traced to a source

Primary Source

Publisher
Apple
Published
2022-03-08

Data Quality

Spec confidence
Vendor claimed
Clock basis
Boost
Core precisions with figures
1 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

Apple M1 Max

SoC · 2021
FP32: 10 TFLOPS
Compare vs M1 Max

Apple M1 Pro

SoC · 2021
FP32: 5.3 TFLOPS
Compare vs M1 Pro

Apple M1

SoC · 2020
FP32: 2.6 TFLOPS
Compare vs M1

Frequently Asked Questions

How many TFLOPS does the Apple M1 Ultra have?

The Apple M1 Ultra delivers 21 TFLOPS FP32 at peak. Flopper does not currently have verified FP16 and FP8 throughput figures for it.

What is the power consumption of the Apple M1 Ultra?

Flopper does not currently have a verified TDP (Thermal Design Power) figure for the Apple M1 Ultra.

How much memory does the Apple M1 Ultra have?

The Apple M1 Ultra is equipped with 128 GB of memory with 800 GB/s of memory bandwidth.

What architecture is the Apple M1 Ultra based on?

The Apple M1 Ultra is based on the Apple M1 architecture, launched in 2022.

How much does the Apple M1 Ultra cost to rent?

Flopper is not tracking any live rental listings for the Apple M1 Ultra. The provider directory lists the clouds that rent comparable accelerators on demand.

When did the Apple M1 Ultra come out?

The Apple M1 Ultra launched in 2022 on the Apple M1 architecture.

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

© 2026 Flopper.io - Compare the GPUs Powering AI