<![CDATA[Ollama + Claude Code / OpenCode making coding free.]]>š—¢š—¹š—¹š—®š—ŗš—® + š—–š—¹š—®š˜‚š—±š—² š—–š—¼š—±š—² / OpenCode

š—”š—»š—± š—¶š˜ š—暝˜‚š—»š˜€ š—°š—¼š—ŗš—½š—¹š—²š˜š—²š—¹š˜† š—¹š—¼š—°š—®š—¹.

No subscriptions. No limits. No data leaving your machine.

Claude Code used to cost $3-$15 per million tokens.

Now you can run it with free open-source models on your computer.

January 16th, 2026: Ollama version 0.14.0 became compatible with Anthropic's messages API.

That means Claude Code now works with any Ollama model.

Zero ongoing costs. Your code never leaves your computer.

Here's the setup:

Download Ollama. Run ollama pull qwen3-coder. Install Claude Code.

Set two environment variables to connect them.

Then run: claude --model qwen3-coder

Give it tasks in plain English:

"Write a function to process images." "Debug why my API calls are failing."

It reads your files. Makes changes. Tests the code. Shows you what it did.

Top models: Qwen 3-Coder for everyday tasks. GPT-OSS 20B for complex projects.

Have an older GPU or lower VRAM, use AirLLM to load only needed parts and run bigger models on the same HW!

This is completely open and free.
Explicitly supported by both tools.
AnyLLM works too.

]]>https://forum.cloudron.io/topic/14937/ollama-claude-code-opencode-making-coding-free.RSS for NodeFri, 17 Apr 2026 18:35:40 GMTFri, 23 Jan 2026 06:46:36 GMT60<![CDATA[Reply to Ollama + Claude Code / OpenCode making coding free. on Sun, 22 Mar 2026 03:01:26 GMT]]>New update making it even simpler to code for free.
https://forum.cloudron.io/topic/15277/ai-devops-opencode-make-coding-free-with-zen-models-no-claude-openai-google

]]>https://forum.cloudron.io/post/122310https://forum.cloudron.io/post/122310Sun, 22 Mar 2026 03:01:26 GMT<![CDATA[Reply to Ollama + Claude Code / OpenCode making coding free. on Sun, 25 Jan 2026 03:07:59 GMT]]>not a fan of claude code, closed source and buggy

loving opencode.ai, TUI and Desktop app all sync with their client/server setup, and easy enough to have many instances running locally and on VPSs

]]>https://forum.cloudron.io/post/119110https://forum.cloudron.io/post/119110Sun, 25 Jan 2026 03:07:59 GMT<![CDATA[Reply to Ollama + Claude Code / OpenCode making coding free. on Sat, 24 Jan 2026 18:15:10 GMT]]>You are welcome @timconsidine

Last night I experimented with having Grok manage an agent I installed in a LAMP container.

The setup was through a custom PHP that could read a custom Python script which could invoke an agent via API.

The idea is to have it be autonomous and self manage itself.

Ran out of steam due to Grok limitations and complications with google libraries.

A useful new Cloudron app could be all this set up as a custom app with ollama, airllm, and a local model so it cannot run out of steam so easily.

The just give it a goal.. and let it Ralph out.

]]>https://forum.cloudron.io/post/119096https://forum.cloudron.io/post/119096Sat, 24 Jan 2026 18:15:10 GMT<![CDATA[Reply to Ollama + Claude Code / OpenCode making coding free. on Sat, 24 Jan 2026 17:41:55 GMT]]>Got Claude Code working with Ollama šŸ‘
Thank you for the information @robi

]]>https://forum.cloudron.io/post/119093https://forum.cloudron.io/post/119093Sat, 24 Jan 2026 17:41:55 GMT<![CDATA[Reply to Ollama + Claude Code / OpenCode making coding free. on Fri, 23 Jan 2026 21:01:06 GMT]]>@timconsidine don't switch. Add another instance to test.

I would like to see AirLLM performance with medium size models for Ralph Wiggum usage.

]]>https://forum.cloudron.io/post/119056https://forum.cloudron.io/post/119056Fri, 23 Jan 2026 21:01:06 GMT<![CDATA[Reply to Ollama + Claude Code / OpenCode making coding free. on Fri, 23 Jan 2026 16:25:58 GMT]]>@robi cool !
Reluctant to switch dev setup mid-project but next one will try it out.
Hoping to get Appflowy and ZeroNet out the door soon.

]]>https://forum.cloudron.io/post/119046https://forum.cloudron.io/post/119046Fri, 23 Jan 2026 16:25:58 GMT<![CDATA[Reply to Ollama + Claude Code / OpenCode making coding free. on Fri, 23 Jan 2026 15:49:28 GMT]]>@timconsidine said in Ollama + Claude Code making coding free.:

My quick look suggested you still need a subscription for Clause Code even if you hook up Ollama model. Did I misunderstand this ?

Yes, only the API needs a sub.

]]>https://forum.cloudron.io/post/119043https://forum.cloudron.io/post/119043Fri, 23 Jan 2026 15:49:28 GMT<![CDATA[Reply to Ollama + Claude Code / OpenCode making coding free. on Fri, 23 Jan 2026 15:24:32 GMT]]>@nebulon said in Ollama + Claude Code making coding free.:

VPS with some nvidia card

I use Koyeb for this kind of thing.
It's a good proposition but I am not needing it much, so may discontinue. Others might find it helpful.

Generally I am happy with my TRAE and desktop Ollama client using one of their cloud models (to avoid pulling it locally).

But everyone raves about Claude Code, so will check them with an Ollama out.

My quick look suggested you still need a subscription for Clause Code even if you hook up Ollama model. Did I misunderstand this ?

]]>https://forum.cloudron.io/post/119042https://forum.cloudron.io/post/119042Fri, 23 Jan 2026 15:24:32 GMT<![CDATA[Reply to Ollama + Claude Code / OpenCode making coding free. on Fri, 23 Jan 2026 14:09:32 GMT]]>I got some Intel Arc Battlemage B580 to test local llm for real. Nvidia is quite trivial to play with, since one can get a VPS with some nvidia card and mostly things are set up ready to use regarding GPU support (it can get very expensive though!)

So it can very likely be the case that this card is woefully underpowered for that use-case, though other similarly sized general purpose models work just fine with ollama. But maybe I miss something obvious with claude code here.

]]>https://forum.cloudron.io/post/119039https://forum.cloudron.io/post/119039Fri, 23 Jan 2026 14:09:32 GMT<![CDATA[Reply to Ollama + Claude Code / OpenCode making coding free. on Fri, 23 Jan 2026 11:21:45 GMT]]>@nebulon which GPU?

]]>https://forum.cloudron.io/post/119031https://forum.cloudron.io/post/119031Fri, 23 Jan 2026 11:21:45 GMT<![CDATA[Reply to Ollama + Claude Code / OpenCode making coding free. on Fri, 23 Jan 2026 10:11:33 GMT]]>I had a go with that lately also on my local setup with a GPU. ollama works well also with openwebui for the models I can run, however I never succeeded to get anything out of claude. If anyone succeeds I would be very happy to hear about the steps to do so. Using qwen3-coder, claude was endlessly spinning the GPU even on small tasks, eventually giving up without ever producing anything šŸ˜•

]]>https://forum.cloudron.io/post/119028https://forum.cloudron.io/post/119028Fri, 23 Jan 2026 10:11:33 GMT<![CDATA[Reply to Ollama + Claude Code / OpenCode making coding free. on Fri, 23 Jan 2026 08:35:36 GMT]]>Wow !
More to play with !

I use ollama desktop with their cloud qwen 3 coder 480b. Iā€™m hoping that connecting Claude code to ollama can make use of that. Will give it a shot.

]]>https://forum.cloudron.io/post/119014https://forum.cloudron.io/post/119014Fri, 23 Jan 2026 08:35:36 GMT