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 3.2+), x86_64

  • Mac OS (10.7+, Lion+), x86_64 or aarch64

• 16 GB+ RAM

• 8+ CPU cores

• Storage: 100 GB available space

Optional features additional requirements

• Provenance and Attribution:

  • Storage: 2 TB available space

Supported IDEs

	IDE	Minimal supported version	Latest supported version	Windows OS	Mac OS	Linux OS
	VS Code	1.68	1.100
	JetBrains IDEs*	2023.2	2025.1
	Eclipse	4.23 (2022-03)	4.35 (2025-03)
	Visual Studio 2022	17.7.4	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:

  • TabNine

  • TabNine-deep-local

  • TabNine-deep-cloud

  • WD-TabNine

  • TabNine-server-runner

  • vdb

  • jdtls

  • typescript-language-server

• Write and execute permissions for the following machine paths:

  • Linux: ~/.config & ~/.tabnine

  • Mac OS: /Users/{{username}}/Library/Preferences & /Users/{{username}}/Library/Application Support

  • Windows: C:\Users\{{username}}\AppData\Roaming\

---

Specs for Deployment + Model Combinations

General Recommendations:

For info on locally deployed models, speak to Support or your Account Manager

AWS

AWS

External Models

Feature	1 - 1000 Users	1001 - 2000 Users	2000+ Users
GPUs	1 × g6e.2xlarge L40S	2 × g6e.2xlarge L40S	4 × g6e.2xlarge L40S
Total Number of GPUs	1	2	4

Azure

Azure

External Models

Feature	1 - 1000 Users	1001 - 2000 Users	2000+ Users
GPUs	1 × NC24ads_A100_v4 A100 80GB	1 × NC40ads_H100_v5 H100 (or 1 × NC48ads A100 v4)	1 × NC80adis H100 v5 (or 1 × NC96ads A100 v4)
Total Number of GPUs	1	1 (or 2)	2 (or 4)

GCP

Google Cloud

External Models

Feature	1 - 1000 Users	1001 - 2000 Users	2000+ Users
GPUs	1 × a2-ultragpu-1g A100 80GB	1 × a2-ultragpu-2g A100 80GB	1 × a2-ultragpu-4g A100 80GB
Total Number of GPUs	1	2	4

On-Premises

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 - 1000 Users	1001 - 2000 Users	2000+ Users
CPU	32	48	72
Memory	72 GB	96 GB	256 GB
Disk	5 TB SSD	8 TB SSD	10 TB SSD
Total Number of GPUs	3 × L40S	3 × H100	6 × H100

---

Tabnine Cluster Requirements (private installation)

Tabnine supports both cloud and on-prem implementations. Contact [e-mail] for specs.

Note: The following GPUs are supported:

• L40S

• A100 (80GB)

• H100 / H200

• B100 / B200

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+