CopperRiverFree Guide

Run AI Models Locally
Complete Local LLM Guide

Stop paying per token. Run open-source AI models on your own hardware — full privacy, zero API costs, complete control. Here's exactly how to do it.

Why run AI locally?

Every time you send a prompt to ChatGPT or Claude, your data leaves your computer, travels to someone else's server, and gets processed on hardware you don't control. You pay per token, you're subject to rate limits, and the provider can change the model, the price, or the privacy policy whenever they want.

Running AI locally flips that equation. The model lives on your machine. Your data never leaves. There are no per-token fees, no rate limits, no outages dependent on someone else's infrastructure.

🔒

Complete privacy

Your prompts, documents, and code never leave your machine. Critical for sensitive data and regulated industries.

💸

Zero per-token cost

No API bills. Run millions of inferences — you pay for electricity, not tokens.

No rate limits

No 429 errors, no usage caps, no queueing. Your hardware, your rules.

🎛️

Full control

Choose the model, the quantization, the context length. Nobody silently changes the model on you.

Hardware requirements

RAM is the bottleneck, not CPU speed. Models live in memory, and bigger models need more of it. Quantization (Q4, Q8) compresses models at a small quality cost.

TierRAMSpeed
Minimum8 GB5-10 t/s (CPU)
Recommended16 GB10-25 t/s
Enthusiast32 GB+25-60 t/s
Server / GPU64 GB+ VRAM60-200+ t/s

Quantization explained

Quantization reduces model precision to save memory. Q4 (4-bit) uses roughly 25% of the original size with minimal quality loss. Q8 (8-bit) uses about 50% with almost no quality loss. FP16 (16-bit) is full precision. For most use cases, Q4 is the sweet spot — you get 90%+ of the model's intelligence at a quarter of the memory cost.

Model selection

Pick the biggest model your hardware can handle. Bigger isn't always better for every task, but it's usually better overall.

ModelParamsBest For
Qwen 3.6 (4B)4BLightweight chat, basic coding
Phi-414BReasoning, math, small footprint
GLM-5.2110B (MoE)General purpose, tool calling, agents
DeepSeek V4671B (MoE)Coding, reasoning, cost-efficient
MiniMax M3230B (MoE)Long context, multilingual
Kimi K32.8T (MoE)Frontier open-source, complex reasoning

Note: MoE (Mixture of Experts) models activate fewer parameters during inference, making them faster and cheaper to run than dense models of the same total size.

Ways to run local AI

ToolTypeSetup
OllamaCLI / APIEasy
llama.cppLibrary / CLIMedium
LM StudioGUI AppEasy
vLLMServerAdvanced
CopperRiverDesktop AppZero setup

Step-by-step: Running your first model

Option A: Ollama (command line)

The fastest way to get started from the terminal.

# Install Ollama (macOS)
brew install ollama

# Start the server
ollama serve

# In another terminal, run a model
ollama run qwen3:4b

# Or run a larger model
ollama run glm5.2

# Use as an OpenAI-compatible API
curl http://localhost:11434/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "qwen3:4b", "messages": [{"role": "user", "content": "Hello!"}]}'

Option B: CopperRiver (zero setup)

If you'd rather not touch the terminal, CopperRiver bundles everything — models, browser, terminal, file access, automation — in a desktop app.

1. Download CopperRiver for Mac
2. Pick a model (GLM, DeepSeek, Qwen, MiniMax, or Kimi)
3. Start chatting

# That's it. No command line, no config files, no GPU setup.
# You also get: web browsing, terminal access, file reading,
# scheduled automations, and agent capabilities — all built in.

Option C: vLLM (production server)

For serving models to multiple users or running agents at scale.

# Install vLLM (requires GPU)
pip install vllm

# Serve a model with OpenAI-compatible API
python -m vllm.entrypoints.openai.api_server \
  --model TheBloke/glm-5.2-AWQ \
  --quantization awq \
  --tensor-parallel-size 1 \
  --port 8000

# Now any OpenAI-compatible client can use it
from openai import OpenAI
client = OpenAI(base_url="http://localhost:8000/v1", api_key="none")
response = client.chat.completions.create(
    model="TheBloke/glm-5.2-AWQ",
    messages=[{"role": "user", "content": "Hello!"}]
)

Performance tips

Use Q4 quantization: Q4 cuts memory usage by 75% with minimal quality loss. For most tasks, you won't notice the difference.
Adjust context length: Longer context = more memory. For chat, 4K-8K tokens is fine. Only use 32K+ when you're processing large documents.
Enable KV cache: KV cache speeds up generation by avoiding recomputation. Most tools enable it by default, but verify.
Close other apps: If your model uses 14GB and your machine has 16GB, Chrome will cause swapping and destroy performance.

What you can do with local AI

Private chatbot

Chat with AI about sensitive documents, code, or personal data — nothing leaves your machine.

Code completion

Get inline code suggestions while you program, without sending your codebase to a third party.

Document analysis

Drop PDFs, contracts, and spreadsheets into a local model. Ask questions, get summaries.

Automation agents

Build agents that browse, run commands, and process files using local models. CopperRiver does this out of the box.

Frequently asked questions

Can I run AI models locally on my computer?

Yes. With 8GB+ RAM you can run small models. For larger models, 16-32GB is recommended. Tools like Ollama and CopperRiver make setup easy — no GPU required for quantized models.

What is the easiest way to run AI locally?

CopperRiver is the easiest — it's a desktop app with models pre-configured, plus browser, terminal, and file access. For CLI users, Ollama is simplest: 'ollama run qwen3:4b'.

Do I need a GPU to run local AI?

No. CPUs can run quantized models at 5-20 tokens per second. GPUs are faster but not required for most use cases.

What are the best open-source models to run locally?

For 8GB RAM: Qwen 3.6 (4B), Phi-4. For 16GB: GLM-5.2 (quantized), DeepSeek V4 (quantized). For 32GB+: full-size models. CopperRiver bundles GLM, DeepSeek, Qwen, MiniMax, and Kimi.

Is running AI locally free?

The models and software are free and open-source. You pay for hardware and electricity. CopperRiver offers managed model hosting and agent capabilities from $9/month.

Run AI locally without the setup

CopperRiver bundles open-source models with browser, terminal, and file access in a Mac desktop app. No command line, no GPU config. Plans from $9/mo.