FluentDBFluentDB
Download
AI models

Run FluentDB's AI locally with Ollama

Point FluentDB at your own Ollama server and the model runs on your Mac. No API key, no token bill, nothing leaves the machine. Bring any model that can call tools and hold more than 4K of context.

By Kevin Piacentini, Software Engineer & Founder of FluentDB

Ollama runs open-weight models on your own hardware. FluentDB talks to it over the local HTTP API, so your schema, your prompts and your queries never go anywhere. No key to rotate, nothing metered, no account.

You're not locked to a single model, either. Any Ollama model that can call tools and hold more than 4K of context will drive the co-pilot. That said, local models are all over the place: one will write you a perfectly nice paragraph and then hand back SQL that doesn't parse. So if you want a straight answer on where to start, it's qwen3-coder, which is what we test on and recommend.

What a model needs to work

You are not tied to one model. Point FluentDB at any Ollama model that clears two bars and it works. Both matter, because the co-pilot leans on each of them to do its job.

More than 4K of context

The model has to hold your schema, the tools it can call, and the conversation so far, all at the same time. A 4,096-token window fills up before a real schema even fits, so anything at or below 4K is out. The more context a model has, the more of your database it can reason about at once.

Native tool calling

The co-pilot runs in a loop: read the schema, call a tool, run something, read the result, decide what's next. A model that can't call a tool reliably can't run that loop, so it can't drive the co-pilot, however well it writes. This is the one plenty of otherwise good local models miss.

Clear both bars and a model will work. How well it writes SQL still varies from one to the next, which is why qwen3-coder is where we tell people to start.

Recommended

Start with qwen3-coder

qwen3-coder

Supported

The one we recommend. A 30B mixture-of-experts coder that only fires 3.3B parameters per token, with native tool calling, 256K of context, and an Apache 2.0 license. It's the best local model we've found for writing SQL against a real schema.

ollama pull qwen3-coder
Full name
Qwen3-Coder-30B-A3B-Instruct
Ollama tag
qwen3-coder (same as :30b)
Architecture
Mixture of Experts
Parameters
30.5B total, 3.3B active per token
Experts
128, with 8 active per token
Layers
48
Context window
262,144 tokens
Quantization
Q4_K_M
Download size
~19 GB (17.3 GiB)
Tool calling
Native, parsed by Ollama
Thinking mode
None. Instruct only
License
Apache 2.0
Released
July 2025

Where it falls short

In our testing the model doesn't cope well with a dead end. When it can't find the right answer it keeps going, and starts making things up rather than stopping. You'll see it most with Auto Run on and AI Read Access off. The query runs, but the model never gets the results back, so it has no way of knowing whether anything worked. Instead of stopping to ask you, it writes another query. Then another. We're working on it.

Set it up in five steps

Ollama does the hosting. FluentDB just talks to it on localhost.

  1. 1Install Ollama from ollama.com, or with brew install ollama.
  2. 2Pull a model. For qwen3-coder, run ollama pull qwen3-coder. It is about 19 GB, so give it a minute.
  3. 3Make sure Ollama is running. It serves on http://localhost:11434 by default.
  4. 4In FluentDB, open Set up AI, choose Ollama (local), and check the server URL matches yours.
  5. 5Pick your model from the list, qwen3-coder or any other with tool calling and 4K-plus context, then save.

Ollama FAQ

Which Ollama models does FluentDB support?

Any model that meets two requirements: it can call tools, and its context window is larger than 4K tokens. That covers a lot of what Ollama can run. The catch is that meeting the bar means a model will work, not that it writes great SQL, which still varies model to model. We recommend qwen3-coder as the place to start.

Does my data leave my Mac when I use Ollama?

No. Ollama runs the model on your own hardware and FluentDB talks to it locally. No API key, and no request to us or to any model vendor.

Do I need an API key to use Ollama?

No, and that's most of the appeal. You need the Ollama app running and the model pulled. Nothing is metered and there's no account.

What hardware do I need for qwen3-coder?

The download is about 19 GB, and those weights stay in memory the whole time the model is loaded, before you add any context. A 32GB Mac handles it comfortably. 24GB works, but you'll feel the squeeze once the context grows.

Is qwen3-coder as good as Claude or GPT?

For everyday queries, it's good. For the hard ones it's behind, and we'd rather just say so. On Spider2, a demanding text-to-SQL benchmark, the 30B scores 21.4 where frontier models get to about 31.1. Use it for daily work, switch to an API model when the question is hard.

Can I use a model other than qwen3-coder?

Yes. Pick any model in your Ollama library that can call tools and holds more than 4K of context, and FluentDB will use it. qwen3-coder is our recommendation, not a requirement. If a model you rely on does not behave, tell us through the support page.

Stop wrestling
with your database.

One database client, one payment, yours forever.

Download for Mac

If FluentDB has not replaced your current client within 14 days, we refund you. No questions asked.