Deploy CF AI Models on Cloudflare Workers AI

Overview

Run CF AI Models directly on Cloudflare Workers AI for edge CDN inference. Local inference offers privacy, zero latency, and no ongoing API costs.

Specs: V8 isolates · Serverless

Installation

bash
Install Ollama — easiest local inference runtime
curl -fsSL https://ollama.com/install.sh | sh
Verify installation
ollama --version

Download Model

bash
Pull CF AI Models (downloads GGUF quantized weights automatically)
ollama pull cf-ai-models
Run interactive chat
ollama run cf-ai-models
Start API server
ollama serve
API available at http://localhost:11434

Python Integration

python
import httpx
from typing import Iterator
class LocalAI:
    """Interface to local CF AI Models running on Cloudflare Workers AI."""
    
    BASE_URL = "http://localhost:11434"
    MODEL = "cf-ai-models"
    
    def chat(self, message: str, system: str = "") -> str:
        """Single-turn chat."""
        resp = httpx.post(
            f"{self.BASE_URL}/api/chat",
            json={
                "model": self.MODEL,
                "messages": [
                    {"role": "system", "content": system},
                    {"role": "user", "content": message}
                ],
                "stream": False
            },
            timeout=120
        )
        resp.raise_for_status()
        return resp.json()["message"]["content"]
    
    def stream(self, message: str) -> Iterator[str]:
        """Streaming chat for real-time output."""
        with httpx.stream(
            "POST",
            f"{self.BASE_URL}/api/chat",
            json={"model": self.MODEL, "messages": [{"role": "user", "content": message}], "stream": True},
            timeout=120
        ) as r:
            for line in r.iter_lines():
                if line:
                    import json
                    chunk = json.loads(line)
                    if not chunk.get("done"):
                        yield chunk["message"]["content"]
Usage
ai = LocalAI()
response = ai.chat("Help me with edge CDN inference")
print(response)
Streaming
for token in ai.stream("Explain edge CDN inference step by step"):
    print(token, end="", flush=True)

Custom Modelfile

bash
Create optimized configuration for edge CDN inference
cat > Modelfile << 'MODELEOF'
FROM cf-ai-models
PARAMETER num_ctx 4096
PARAMETER temperature 0.7
PARAMETER top_p 0.9
SYSTEM "You are an AI assistant specialized in edge CDN inference. You run locally on Cloudflare Workers AI. Be concise, accurate, and helpful."
MODELEOF
ollama create edge-CDN-inference-assistant -f Modelfile
ollama run edge-CDN-inference-assistant

Performance Profile

MetricValue

HardwareV8 isolates MemoryServerless Speed10-40 tokens/sec (CPU) / 40-100+ tok/s (GPU) First token<200ms (GPU) / <1s (CPU) Context4096-32768 tokens Cost$0 (after hardware)

Production Setup with FastAPI

python
from fastapi import FastAPI
from pydantic import BaseModel
app = FastAPI(title="Cloudflare Workers AI AI API")
ai = LocalAI()
class ChatRequest(BaseModel):
    message: str
    system: str = ""
class ChatResponse(BaseModel):
    response: str
    model: str
    device: str
@app.post("/chat", response_model=ChatResponse)
async def chat_endpoint(req: ChatRequest):
    response = ai.chat(req.message, req.system)
    return ChatResponse(response=response, model="CF AI Models", device="Cloudflare Workers AI")
@app.get("/health")
async def health():
    return {"status": "ok", "model": "CF AI Models", "device": "Cloudflare Workers AI"}

Troubleshooting

Slow inference: Switch to Q4_K_M quantization, reduce context window Out of memory: Use smaller model or Q3_K_S quant GPU not used: Install CUDA/Metal drivers, check ollama logs High latency: Warm up model by sending a dummy request on startup

Resources