Razer AIKit · Local AI

Independent Resources on Razer AIKit andRazer AVA

Verified guides to Razer AIKit and independent tracking of Razer AVA's public developer status. Receive updates when official information changes.

WHAT IS RAZER AIKIT?

Razer AIKit is an open-source, preview-stage AI development environment that brings cloud-grade performance to your desktop. Run large language models (LLMs) locally on NVIDIA GPUs, scale inference across a GPU cluster with Ray and vLLM, fine-tune with LoRA via LlamaFactory, and explore 300,000+ models from Hugging Face — all through a Docker Compose stack with Open WebUI, Jupyter Lab, Grafana and Prometheus.

▸Local-first AI: run LLMs on-device for total privacy and zero latency
▸Multi-GPU scaling with Ray for distributed inference
▸vLLM engine with PagedAttention for memory-efficient serving
▸LoRA fine-tuning with LlamaFactory
▸NVIDIA GPUs (Compute Capability 7.0+): RTX 20/30/40/50, Blackwell, Hopper, Ada, Ampere
▸Ubuntu 22.04/24.04, Windows 11 via WSL2, x86-64 & ARM64
START HERE

Verified Razer AI resources

Independent guides that separate confirmed product information from community interpretation.

THE CORE ARCHITECTURE
01

vLLM Engine

High-throughput, memory-efficient LLM inference. vLLM uses PagedAttention to serve local models at state-of-the-art speed on a single GPU or a cluster.

02

Ray

Distributed computing framework for scaling AI across GPUs. Ray orchestrates multi-GPU inference and manages resources efficiently for smooth multitasking.

03

LlamaFactory

Parameter-efficient fine-tuning toolkit. Predefined recipes to fine-tune Llama and other open models with LoRA for gaming and assistance contexts.

04

Open WebUI

Built-in local chat interface on port 1919. Interact with your models on-device, fully offline, through a clean web UI.

05

Docker & Dev Tools

Docker Compose stack with Jupyter Lab (8888), Grafana (3000) and Prometheus (9090) for notebooks, monitoring and observability.

06

AIKit CLI

Model lifecycle management from the terminal with rzr-aikit. Clone, run and fine-tune models pulled from 300,000+ Hugging Face checkpoints.

FOLLOW RAZER AI UPDATES

Receive updates when Razer publishes confirmed changes to AIKit, AVA, or their public developer paths.

AIKit guide:Requirements, official setup, and scope.

AVA status:Independent tracking of public SDK and beta information.

Primary sources:Links to Razer and the official AIKit repository.

Updates:A notification when official product information changes.