$cd ../guides/
πŸ–₯ Hardware GuideRaspberry Pi 5Budget Pick

Raspberry Pi 5:
The $80 AI Server

/** The honest guide. What actually works, what doesn't, and how to squeeze the most out of 8GB RAM. */

// Honest reality check before you buy
βœ“ Pi 5 works well for lightweight AI tasks: simple chat, reminders, Notion queries, webhook processing
βœ— Too slow for large models (7B+) in real-time conversation
βœ“ Great as a dedicated controller if you route heavy inference to a cloud API (Claude/GPT-4o)
β†’ Compare to Mac Mini M4 Pro β€” 10x faster inference
$80
Total Cost
// Pi 5 8GB + case
5W
Idle Power
// < $1/month
16 t/s
gemma2:2b
// Best for Pi 5
ARM
Architecture
// Cortex-A76 quad
model_compatibility.log

πŸ€– Model Compatibility on Pi 5 (8GB RAM)

βœ“phi3:mini (3.8B)8 tok/s
βœ“llama3.2:3b11 tok/s
βœ“gemma2:2b16 tok/s
βœ“mistral:7b3 tok/s
βœ—llama3.1:8b< 1 tok/s
config.yaml

βš™οΈ Recommended Config for Pi 5

# Optimized for Raspberry Pi 5 8GB
ai:
provider: "ollama"
model: "llama3.2:3b" # sweet spot on Pi 5
num_threads: 4 # use all 4 cores
context_length: 2048 # smaller = faster on Pi
routing:
complex: # heavy tasks β†’ cloud
provider: "anthropic"
setup.sh

πŸš€ Setup Steps

# 1. Flash Raspberry Pi OS (64-bit) to SD card
# 2. Enable SSH, connect to network
# 3. Install Ollama
$ curl -fsSL https://ollama.ai/install.sh | sh
$ ollama pull llama3.2:3b
# 4. Install OpenClaw
$ curl -fsSL https://openclaw.ai/install.sh | bash
# 5. Enable auto-start on Pi boot
$ sudo systemctl enable openclaw
$ sudo systemctl start openclaw
← Back to Guides