What is the latest version of AMD Instinct MI355X?

The current shipped version of AMD Instinct MI355X is MI355X, as of September 15, 2026.

How much does AMD Instinct MI355X cost?

AMD Instinct MI355X has no published flat entry price. Enterprise GPU hardware pricing not published

What AI model does AMD Instinct MI355X use?

AMD Instinct MI355X runs primarily on CDNA 4.

← Chips & Compute

AMD Instinct MI355X

Name: AMD Instinct MI355X
Author: AMD

AMD · #10 most active of 18 in Chips & Compute

Compare →

288GB HBM3E accelerators with the ROCm software stack, used by several inference providers.

100

Trust score · Verified

2 data points checked · 2026-09-11

Model stack: VerifiedEntry price: UnverifiableVersion: VerifiedHow this works →

Current version

MI355X

Entry cost

Enterprise GPU hardware pricing not published

Changes / 30d

The short answers · verified September 15, 2026

What is the latest version of AMD Instinct MI355X?: The current shipped version of AMD Instinct MI355X is MI355X, as of September 15, 2026.
How much does AMD Instinct MI355X cost?: AMD Instinct MI355X has no published flat entry price. Enterprise GPU hardware pricing not published
What AI model does AMD Instinct MI355X use?: AMD Instinct MI355X runs primarily on CDNA 4.

Source: AMD — rocm.docs.amd.com · Reusable under CC BY 4.0 — cite Tomorrow

Capabilities

288GB HBM3E
FP4/FP6 support
ROCm 7
open rack designs
DPX compute partition mode
CPX compute partition mode
NPS2 memory partitioning
GPU virtualization support
SR-IOV support
CDNA4 microarchitecture
ROCm Core SDK support
SR-IOV deployments
GPU partitioning (DPX, CPX)
ROCm support
CDNA4 architecture
GPU Partitioning
DPX Compute Partition Mode
CPX Compute Partition Mode
NPS2 Memory Partitioning
SR-IOV Deployments
vLLM Support
PyTorch Support
JAX Support
GPU computing
AI inference
HPC
GPU partitioning
GPU Virtualization
DPX Compute Partition
CPX Compute Partition
CDNA4 Architecture
ROCm Support
SR-IOV virtualization
GPU compute partition
DPX compute partition
CPX compute partition
ROCm 7.14.0 support
SR-IOV deployment
AI inference optimization
SR-IOV
vLLM support
PyTorch support
JAX support
GPU partitioning support
SGLang support
ROCm 7.14.0 compatibility
GPU virtualization
HPC workloads
GPU compute partitioning
ROCm Core SDK 7.14.0
GPu Virtualization support
CDNA4
ROCm 10.0.0 Support
GPU Virtualization Support
AI Inference Acceleration
Symmetric Memory Support
ROCm 10.0.0 support
Passthrough support
Passthrough Ubuntu 22.04
SR-IOV Support
SGLang Support
Symmetric Memory
Triton Operator Tracing
Passthrough Ubuntu
HIP support
ROCm Core SDK
GPU Virtualization (SR-IOV)
MI350 microarchitecture
Passthrough Virtualization
AI Inference
HPC Workloads
Passthrough Support
CDNA4 Microarchitecture
ROCm Core SDK 10.0.0 Support
TensorFlow Support
AI training

Pricing

Open Source
Free open-source software platform for AMD Instinct GPUs
Free

Entry price over time

8/25/2026 · $09/16/2026 · $0

Geek mode

Models under the hood

CDNA 4
AMD
disclosed
ROCm
AMD
disclosed

Context window

—

Public API

Multi-model routing

Stack signals

ROCm
CDNA4
HIP

Shared model stack

Other tracked products running on the same foundation models — a quick read on how much of the catalog moves when one of these models changes.

CDNA 4AMD · 1 product
- AMD Instinct MI355X
ROCmAMD · 1 product
- AMD Instinct MI355X

green disclosed · amber inferred · grey unattributed. Aliases are folded into one model; provider concentration counts only models with an established vendor.

Reported scale

Reference data. Each figure is whatever the source actually said — weekly users, downloads, revenue run-rate — with its own definition and date. These are not comparable between tools and are never used to rank anything.

No public usage figure on record for this product.

Public market scorecard

AMD investor relations

AMD trades as NASDAQ: AMD. Figures below are as reported for Q2 2026 on Aug 4, 2026; market levels are the close on Aug 6, 2026 and are a reference marker, not a live quote.

Q2 2026 revenue

~$9.5B

+30% YoY

Data center segment: ~$4.5B; MI series ramp
Gross margin: ~54%

Market reference

Share price~$190

12-month change+35%

Market cap~$310B

Live quote

Also in Chips & Compute

All Chips & Compute

Tenstorrent Blackhole

Tenstorrent

Open RISC-V AI hardware

Version: Blackhole
Cost: from $999/unit
Model: Tensix cores

Google TPU Ironwood

Google

Inference-first TPU pods

Version: Ironwood (7th generation)
Cost: from $5.4/unit
Model: Gemini

Cerebras WSE-3

Cerebras

Wafer-scale inference and training

Version: WSE-3
Cost: Free tier / developer tier pricing available (contact/partner integrations)
Model: Codex-Spark

NVIDIA Blackwell

NVIDIA

GB200/B200 rack-scale AI systems

Version: Blackwell
Cost: Pricing is not publicly listed (enterprise hardware architecture/system)
Model: Blackwell

AWS Trainium2

AWS

Cloud-native training silicon

Version: Trainium2
Cost: Pricing not published; available via AWS EC2 instance pricing.
Model: Neuron compiler

Intel Gaudi 3

Intel

Cost-focused training and inference accelerator.

Version: 1.24.1
Cost: Pricing not published. Available via Intel Tiber AI Cloud or OEM platforms.
Model: Accelerator

Change history

Sep 15, 2026first seenversion
AMD Instinct MI355X moved to MI355X
ROCm 10.0.0MI355X
source
Aug 27, 2026first seenversion
AMD Instinct MI355X moved to CDNA4
MI355XCDNA4
source
Aug 27, 2026first seencapability
New capabilities: ROCm 10.0.0 Support, GPU Virtualization Support, AI Inference Acceleration
52 tracked56 tracked · +ROCm 10.0.0 Support, GPU Virtualization Support, AI Inference Acceleration, Symmetric Memory Support
source
Aug 26, 2026announcedversion
AMD Instinct MI355X moved to MI355X
CDNA4MI355X
source
Aug 26, 2026announcedcapability
New capabilities: ROCm 10.0.0 support
56 tracked57 tracked · +ROCm 10.0.0 support
source
Aug 26, 2026announcedversion
AMD Instinct MI355X moved to ROCm 10.0.0
MI355XROCm 10.0.0
source
Aug 26, 2026announcedcapability
New capabilities: TensorFlow Support
74 tracked75 tracked · +TensorFlow Support
source
Aug 26, 2026announcedcapability
New capabilities: ROCm Core SDK 10.0.0 Support
73 tracked74 tracked · +ROCm Core SDK 10.0.0 Support
source
Aug 26, 2026announcedcapability
New capabilities: Passthrough support
57 tracked58 tracked · +Passthrough support
source
Aug 26, 2026announcedcapability
New capabilities: AI training
75 tracked76 tracked · +AI training
source
Aug 26, 2026announcedcapability
New capabilities: Passthrough Ubuntu 22.04
58 tracked59 tracked · +Passthrough Ubuntu 22.04
source
Aug 26, 2026announcedcapability
New capabilities: SR-IOV Support, SGLang Support, Symmetric Memory
59 tracked63 tracked · +SR-IOV Support, SGLang Support, Symmetric Memory, Triton Operator Tracing
source
Aug 26, 2026announcedcapability
New capabilities: Passthrough Ubuntu
63 tracked64 tracked · +Passthrough Ubuntu
source
Aug 26, 2026announcedcapability
New capabilities: HIP support, ROCm Core SDK
64 tracked66 tracked · +HIP support, ROCm Core SDK
source
Aug 26, 2026announcedcapability
New capabilities: GPU Virtualization (SR-IOV)
66 tracked67 tracked · +GPU Virtualization (SR-IOV)
source
Aug 26, 2026announcedversion
AMD Instinct MI355X moved to ROCm 10.0.0
MI355XROCm 10.0.0
source
Aug 26, 2026announcedversion
AMD Instinct MI355X moved to MI355X
ROCm 10.0.0MI355X
source
Aug 26, 2026announcedcapability
New capabilities: MI350 microarchitecture
67 tracked68 tracked · +MI350 microarchitecture
source
Aug 26, 2026announcedcapability
New capabilities: Passthrough Virtualization
68 tracked69 tracked · +Passthrough Virtualization
source
Aug 26, 2026announcedcapability
New capabilities: AI Inference
69 tracked70 tracked · +AI Inference
source
Aug 26, 2026announcedcapability
New capabilities: HPC Workloads, Passthrough Support, CDNA4 Microarchitecture
70 tracked73 tracked · +HPC Workloads, Passthrough Support, CDNA4 Microarchitecture
source
Aug 7, 2026first seencapability
New capabilities: GPU partitioning (DPX, CPX), ROCm support, CDNA4 architecture
123
source
Aug 6, 2026first seencapability
New capabilities: SR-IOV deployments
115
source
Aug 4, 2026first seencapability
New capabilities: CDNA4 microarchitecture, ROCm Core SDK support
96
source
Aug 3, 2026first seencapability
New capabilities: DPX compute partition mode, CPX compute partition mode, NPS2 memory partitioning
45
source
Jul 15, 2026announcedcapability
New capabilities: GPU Partitioning, DPX Compute Partition Mode, CPX Compute Partition Mode
15 tracked23 tracked · +GPU Partitioning, DPX Compute Partition Mode, CPX Compute Partition Mode, NPS2 Memory Partitioning, SR-IOV Deployments, vLLM Support, PyTorch Support, JAX Support
source
Jul 15, 2026announcedcapability
New capabilities: GPU computing, AI inference, HPC
23 tracked27 tracked · +GPU computing, AI inference, HPC, GPU partitioning
source
Jul 15, 2026announcedcapability
New capabilities: ROCm 7.14.0 support
36 tracked37 tracked · +ROCm 7.14.0 support
source
Jul 15, 2026announcedcapability
New capabilities: CDNA4 Architecture, ROCm Support
30 tracked32 tracked · +CDNA4 Architecture, ROCm Support
source
Jul 15, 2026announcedcapability
New capabilities: SR-IOV, vLLM support, PyTorch support
39 tracked43 tracked · +SR-IOV, vLLM support, PyTorch support, JAX support
source
Jul 15, 2026announcedcapability
New capabilities: GPU Virtualization, DPX Compute Partition, CPX Compute Partition
27 tracked30 tracked · +GPU Virtualization, DPX Compute Partition, CPX Compute Partition
source
Jul 15, 2026announcedcapability
New capabilities: GPU compute partition, DPX compute partition, CPX compute partition
33 tracked36 tracked · +GPU compute partition, DPX compute partition, CPX compute partition
source
Jul 15, 2026announcedcapability
New capabilities: GPU partitioning support, SGLang support, ROCm 7.14.0 compatibility
43 tracked46 tracked · +GPU partitioning support, SGLang support, ROCm 7.14.0 compatibility
source
Jul 15, 2026announcedcapability
New capabilities: SR-IOV virtualization
32 tracked33 tracked · +SR-IOV virtualization
source
Jul 15, 2026announcedcapability
New capabilities: SR-IOV deployment, AI inference optimization
37 tracked39 tracked · +SR-IOV deployment, AI inference optimization
source
Jul 15, 2026announcedversion
AMD Instinct MI355X moved to ROCm 7.14.0
MI355XROCm 7.14.0
source
Jul 15, 2026announcedcapability
New capabilities: ROCm Core SDK 7.14.0, GPu Virtualization support
49 tracked51 tracked · +ROCm Core SDK 7.14.0, GPu Virtualization support
source
Jul 15, 2026announcedcapability
New capabilities: GPU virtualization
46 tracked47 tracked · +GPU virtualization
source
Jul 15, 2026announcedcapability
New capabilities: GPU compute partitioning
48 tracked49 tracked · +GPU compute partitioning
source
Jul 15, 2026announcedcapability
New capabilities: HPC workloads
47 tracked48 tracked · +HPC workloads
source

Subscribe to AMD Instinct MI355X changes

AMD Instinct MI355X compared

Straight head-to-head pages against the busiest products in Chips & Compute.

AMD Instinct MI355X vs Tenstorrent Blackhole AMD Instinct MI355X vs Google TPU Ironwood AMD Instinct MI355X vs Cerebras WSE-3 AMD Instinct MI355X vs NVIDIA Blackwell AMD Instinct MI355X vs AWS Trainium2 AMD Instinct MI355X vs Intel Gaudi 3

How to cite this page

Free to cite and reuse under CC BY 4.0. Permalink: https://tomorrow.aliensquad.ai/tools/amd-instinct

APA

Tomorrow. (2026). AMD Instinct MI355X — version, pricing and model stack [Data set entry]. AlienSquad. Retrieved 2026-09-17, from https://tomorrow.aliensquad.ai/tools/amd-instinct

BibTeX

@misc{tomorrow-tools-amd-instinct,
  author       = {{Tomorrow}},
  title        = {AMD Instinct MI355X — version, pricing and model stack},
  year         = {2026},
  publisher    = {AlienSquad},
  howpublished = {\url{https://tomorrow.aliensquad.ai/tools/amd-instinct}},
  note         = {Accessed: 2026-09-17}
}