System Requirements
Tabnine AI code assistant: System requirements
Tabnine Client Requirements
The Tabnine client runs as an IDE plugin/extension on the end user's machine.
Machine specs
OS/Arch of the following:
Windows (Windows 10+), x86_64 or i686
Linux (kernel 6.2+), x86_64
Mac OS (12+), x86_64 or aarch64
16 GB+ RAM
8+ CPU cores
Storage: 100 GB available space
Supported IDEs

VS Code
1.85
1.105

JetBrains IDEs*
2023.2
2025.2

Eclipse
4.28 (2023-06)
4.36 (2025-06)

Visual Studio 2022
17.10
17.14
* JetBrains IDEs including IntelliJ, PyCharm, WebStorm, PhpStorm, GoLand, RubyMine, CLion, AppCode, Rider, DataGrip, and Android Studio
Network connection
Connection to the Tabnine cluster on port 443
Recommended for the initial install: Access to the IDE marketplaces (i.e., VS Code Marketplace, JetBrains Plugin Marketplace)
Permissions
Execute permissions for the following executables:
TabNineTabNine-deep-localTabNine-deep-cloudWD-TabNineTabNine-server-runnervdbjdtlstypescript-language-server
Write and execute permissions for the following machine paths:
Linux:
~/.config & ~/.tabnineMac OS:
/Users/{{username}}/Library/Preferences & /Users/{{username}}/Library/Application SupportWindows:
C:\Users\{{username}}\AppData\Roaming\
Specs for Deployment + Model Combinations
General Recommendations:

AWS
External Models
Feature
1 - 200 Users
201 - 500 Users
501-1000 Users
1001-2000 Users
2000+ Users
GPUs
1 x g6e.2xlarge L40S
1 x g6e.2xlarge L40S
2 x g6e.2xlarge L40S
3 x g6e.2xlarge L40S
4 x g6e.2xlarge L40S
Azure
External Models
Feature
1 - 200 Users
201-500 Users
501-1000 Users
1001-2000 Users
2000+ users
GPUs
1 x NC40ads_H100_v5 H100 94GB
1 x NC40ads_H100_v5 H100 94GB
1 x NC40ads_H100_v5 H100 94GB
2 x NC40ads_H100_v5 H100 94GB
3 x NC40ads_H100_v5 H100 94GB
Google Cloud
External Models
Feature
1 - 200 Users
201-500 Users
501-1000 Users
1001-2000 Users
2000+ Users
GPUs
1 x a3-highgpu-1g H100 80GB
1 x a3-highgpu-1g H100 80GB
1 x a3-highgpu-1g H100 80GB
1 x a3-highgpu-1g H100 80GB
2 x a3-highgpu-1g H100 80GB
On-Premises Kubernetes 
Tabnine Enterprise can be installed on a new or existing Kubernetes cluster. For customers installing on a brand new Kubernetes cluster, we recommend the following minimum hardware specifications for the Kubernetes control-plane only (non-inclusive of Tabnine requirements).
Specs (Per Node)
HA
Non-HA
Number of Nodes
3
1
CPU
4 CPU
4 CPU
Memory
16 GB
16 GB
Disk
256 GB SSD
256 GB SSD
Network
1 GbE
1 GbE
Operating System
RHEL or Ubuntu
RHEL or Ubuntu
On-Premises
Specs (Minimum)
1 - 200 Users
201 - 500 Users
501-1000 Users
1001-2000 Users
2000+ Users
CPU
64
64
72
72
96
Memory
144 GB
144 GB
192 GB
192 GB
256 GB
Disk
10 TB SSD
10 TB SSD
16 TB SSD
16 TB SSD
32 TB SSD
GPUs
4 x RTX 6000 PRO Blackwell OR 4 x L40S
4 x RTX 6000 PRO Blackwell OR 4 x L40S
4 x H100
6 x H100
10 x H100
Tabnine Cluster Requirements (private installation)
Tabnine supports both cloud and on-prem implementations. Contact [email protected] for specs.
Note: The following GPUs are supported:
L40S
RTX PRO 6000 Blackwell
A100 (80GB)
H100 / H200
B100 / B200
Optional features / additional requirements
Provenance and Attribution:
Storage: 5 TB available space
Domain Name System (DNS)
DNS configured with an A or CNAME record for the load balancer where the application will be exposed.
TLS Certificate
TLS certificate and private key issued and signed by a certificate authority that you trust (key and certificate in PEM format).
Network Connection
Connection to Tabnine container registry:
Host: registry.tabnine.com
IP: 34.72.243.185
Port: 443
Connection to Tabnine logs gateway for collecting metrics and logs (optional):
Host: logs-gateway.tabnine.com
IP: 34.123.33.186
Port: 443
Databases
Redis version 6.5+
PostgreSQL version 15.0+
Last updated
Was this helpful?
