System Requirements | Kamiwaza Docs

Documentation for Kamiwaza 0.9.3

This version of Kamiwaza is no longer actively maintained. For the current GA release, see 1.0.1.


Base System Requirements

Supported Operating Systems & Architecture

CPU Requirements

Core Software Requirements

Memory Requirements

System RAM

GPU Memory (vRAM)

Storage Requirements

Storage Performance

Storage Capacity

Linux/macOS

Hardware Recommendation Tiers

Kamiwaza is a distributed AI platform built on Ray that supports both CPU-only and GPU-accelerated inference. Hardware requirements vary significantly based on:

GPU Memory Requirements by Model Size

The table below provides real-world GPU memory requirement estimates for representative models at different scales.

Model Example Parameters Minimum vRAM Notes
GPT-OSS 20B 20B 24GB Fits 1x 24GB GPU
GPT-OSS 120B 120B 80GB 1x H100/H200 or 2x A100 80GB recommended
Qwen 3 235B A22B 235B 150GB 2x H200 (282GB) or 2x B200 (384GB) ideal
Qwen 3-VL 235B A22B 235B 150GB Budget +20-30% vRAM for high-res vision inputs

Tier 1: Development & Small Models

Use Case: Local development, testing, small to medium model deployment (up to 13B parameters) Hardware Specifications:

Tier 2: Production - Medium to Large Models

Use Case: Production deployment of medium to large models (13B-70B parameters), high throughput Hardware Specifications:

Tier 3: Enterprise Multi-Node Cluster

Use Case: Enterprise deployment with multiple models, high availability, horizontal scaling, 99.9%+ SLA Cluster Architecture:

Cloud Provider Instance Mapping

AWS EC2 Instance Types

Tier Instance Type vCPU RAM GPU Storage
Tier 1: CPU-only m6i.2xlarge 8 32GB None 200GB gp3
Tier 1: With GPU g5.xlarge 4 16GB 1x A10G (24GB) 200GB gp3

Google Cloud Platform (GCP) Instance Types

Tier Machine Type vCPU RAM GPU Storage
Tier 1: CPU-only n2-standard-8 8 32GB None 200GB SSD
Tier 1: With GPU n1-standard-8 + 1x T4 8 30GB 1x T4 (16GB) 200GB SSD

Microsoft Azure Instance Types

Tier VM Size vCPU RAM GPU Storage
Tier 1: CPU-only Standard_D8s_v5 8 32GB None 200GB Premium SSD
Tier 1: With GPU Standard_NC4as_T4_v3 4 28GB 1x T4 (16GB) 200GB Premium SSD

Dependencies & Components

Required System Packages

See platform-specific installation instructions

NVIDIA Components (Linux GPU Support)

Docker Configuration Requirements

Network Configuration

Network Bandwidth Requirements

Single Node Deployment

Special Considerations

Apple Silicon (M-Series)

MLX Engine Support: