aitoolcompass.

Find your next AI tool

Search by product name or task. Press Escape to close.

LLMKube

● Identity checked

Assistant · Vendor site 2026-10-04

LLMKube is an open-source Kubernetes operator for self-hosted LLM inference across NVIDIA, Apple Silicon, and AMD hardware, supporting runtimes such as vLLM, llama.cpp, and mlx-server with CLI deployment, autoscaling, GPU sharding, and Grafana metrics.

Updated 2026-10-04View sources
Official website
Category
Assistant
Free access
Project is described as open source on the homepage with public documentation and GitHub access.
API access
Not confirmed

Is LLMKube right for you?

A good fit for

Platform and ML teams that want Kubernetes-native orchestration for local or private-cloud LLM inference instead of per-token cloud APIs.

Before you choose

You supply clusters, GPUs, and operational expertise; LLMKube does not publish a hosted SaaS price list.

Production LLMs on your fleet

LLMKube targets teams scaling beyond single-machine Docker setups by adding HPA autoscaling, inference metrics, and pluggable LLM runtimes under Kubernetes control.

What it can do

Features & capabilities

Unknown is different from unavailable. Each fact carries its own evidence.

CapabilityValueEvidenceChecked
Kubernetes operatorHomepage markets LLMKube as a Kubernetes operator for self-hosted inference with vLLM, llama.cpp, and related runtimes.Facts sourced2026-10-04
CLI deploySite shows llmkube CLI commands to deploy named models with selectable GPU runtimes.Facts sourced2026-10-04
Hardware supportHeader badges list Kubernetes native support for NVIDIA, Apple Silicon, and AMD accelerators.Facts sourced2026-10-04

Understand the total cost

LLMKube pricing & plans

Pricing

Not listed

Official monthly price not confirmed

API
Not confirmed
LLMKube pricing, plans and price history

Alternatives to LLMKube

View all ↗

The practical questions

Frequently asked questions

What is LLMKube used for?

LLMKube is an open-source Kubernetes operator for self-hosted LLM inference across NVIDIA, Apple Silicon, and AMD hardware, supporting runtimes such as vLLM, llama.cpp, and mlx-server with CLI deployment, autoscaling, GPU sharding, and Grafana metrics.

Does LLMKube have a free plan?

Project is described as open source on the homepage with public documentation and GitHub access.. This record does not confirm an ongoing free plan.

How much does LLMKube cost?

A listed monthly price has not been confirmed. See the plan cards for entitlements, billing commitments and seat minimums.

Can I use LLMKube through an API?

Not confirmed. API access and subscription access may have different terms; consult the linked sources.

What should I check before choosing it?

You supply clusters, GPUs, and operational expertise; LLMKube does not publish a hosted SaaS price list.

Price history

No retained pricing changes yet. A current price alone does not establish a historical trend.

How this profile is supported

Facts apply to the named version and check date. Send a sourced correction if something changed.