The Distributed Open Llama Network

Your GPU is idle.
Someone's agent needs it.

Share spare compute with the network. Use Qwen3 8B for free in Claude Code, Continue, and other agentic tools. No tokens, no fees — just a community.

Install dollama How it works
qwen3:8b 8B parameters Ollama-native Anthropic API
dollama mascot
-- nodes online
Qwen3 8B
-- requests today
How it works

Folding@Home, but for LLM inference

01

Install & choose your role

Grab the dollama CLI. Run as a user to consume inference, as a contributor to share compute, or both to do it all.

02

The network connects you

The coordinator matches user requests with available contributor nodes. All traffic routes through our relay — your files and context never leave your machine.

03

Free inference, forever

No tokens, no billing, no blockchain. Contributors earn priority in a leaderboard. The more you give, the faster your own requests get served.

💻
You
Coordinator
⚙️
Contributor
✅
Response
Choose your path

Use it, share it, or do both

USE
I need inference

Use the network

Point your coding tools at dollama's local proxy. It forwards your LLM requests to the network and streams responses back. Your code and context stay local — only the inference is offloaded.

$ dollama connect
GIVE
I have spare compute

Serve the network

If you have Ollama running with Qwen3 8B pulled, donate your idle cycles. The CLI registers your node with the coordinator and handles incoming inference requests automatically.

$ dollama serve
Get started

Install in one command

🦙
Ollama
Required runtime
💾
8GB+ RAM
Recommended
💻
macOS / Linux / Win
Cross-platform
🧠
qwen3:8b
Network model
Terminal 
curl -fsSL https://dollama.net/install.sh | sh

Requires Ollama installed with qwen3:8b pulled if you plan to contribute.

PowerShell 
irm https://dollama.net/install.ps1 | iex

Requires Ollama installed with qwen3:8b pulled if you plan to contribute.

Configure

Use with Claude Code

1

Start the proxy

Run dollama connect to start the local proxy on port 11411. This exposes an Anthropic-compatible Messages API endpoint.

2

Add to your Claude Code settings

Copy the JSON config into ~/.claude/settings.json. This sets the base URL and auth token so Claude Code routes requests through the dollama network.

3

Use it

That's it. Claude Code will use the network model for inference. Your main Claude model stays unchanged — only the configured model routes through dollama.

tip

Want to contribute too?

Run dollama both instead — it starts the proxy and registers your machine as a contributor node in one command.

~/.claude/settings.json 
{
  "env": {
    "ANTHROPIC_BASE_URL": "http://localhost:11411",
    "ANTHROPIC_AUTH_TOKEN": "olm_your_token_here"
  },
  "model": "network:qwen3:8b"
}
Or set env vars directly 
export ANTHROPIC_BASE_URL=http://localhost:11411
export ANTHROPIC_AUTH_TOKEN=olm_your_token_here
Pull the model (contributors) 
ollama pull qwen3:8b
Live network

The herd at a glance

--
Nodes online
Active contributors right now
--
Tokens processed
Total inference served
--
Requests completed
Successful inferences

Contributor Leaderboard preview

RankContributorCompute
1 gpu-farm-42 482,100 tok
2 inference-node-alpha 310,850 tok
3 llm-volunteer-99 198,420 tok
4 weekend-contributor 87,300 tok
5 idle-gpu-donor 45,670 tok
FAQ

Common questions

No. Contributor nodes only receive the LLM inference prompt and return generated tokens. Your files, repository context, and working directory never leave your machine. The local proxy handles all context assembly — contributors see only the raw inference request.
Network activity is monitored for load balancing and improving routing — otherwise all data is protected. Contributor nodes only see inference prompts, never your files, repo context, or working directory. No data is sold or shared with third parties. End-to-end encryption is planned for a future phase.
Qwen3 8B hits the sweet spot: fast enough to run on consumer hardware (including laptops with decent GPUs), capable enough for agentic coding tasks like tool calls and code edits. A single model across the network keeps things simple and lets us optimize routing. More models may come in future phases.
Ollama installed and running, with qwen3:8b pulled. Then just run dollama serve. The CLI handles registration, heartbeats, and inference routing automatically. Any machine that can run Ollama can contribute — dedicated GPUs are great, but even a modern CPU works.
The coordinator tracks contribution — how many tokens your node has served, uptime, reliability. When you submit a request as a user, your contribution history gives you priority in the queue. Think of it as karma, not currency. No financialization, no speculation.
Yes. The local proxy exposes an Anthropic Messages API endpoint at localhost:11411. Any tool that supports a custom Anthropic-compatible base URL can use it — Continue, Aider, or your own scripts. We're focused on agentic coding tools but the API is standard.
We like llamas — Ollama is the backbone of this project. But a doe felt right for what we're building: gentle, graceful, and part of a herd. Plus, dollama → doe. It was right there the whole time.