Written by Jakub Rusinowski · Last updated 2026-07-12 · Hardware figures computed by our VRAM engine
Point Aider at Ollama with `aider --model ollama_chat/qwen3.6:27b` and it runs fully local — no API key, no code leaving your machine, every change a revertible git commit. The catch: Aider depends on models following strict edit formats, so it rewards the 22B+ class (Qwen 3.6 27B, Devstral-2 22B); below that, expect malformed edits often enough to annoy.
Aider is the terminal pair programmer: it maps your repo, takes instructions in plain English, and applies the model's edits as clean git commits. That git-native loop is *more* valuable with local models than with frontier ones — when a smaller model occasionally fumbles an edit, git revert makes the mistake free.
The flip side: Aider communicates edits through structured formats (diffs or search/replace blocks), and producing them *exactly* is a capability test many small models fail. This page is the local-specific setup plus the honest model list. For what Aider is versus Continue/Cline/Tabby, see the tool matrix.
python -m pip install aider-install && aider-install
curl http://localhost:11434 # → "Ollama is running"Aider is a Python CLI; Ollama setup is covered in our install guide if you're starting from zero.
The tier list, from our testing and the compute engine's fit math:
# 24 GB card — the reliable tier
ollama pull qwen3.6:27b
# 16 GB card — the floor for dependable edits
ollama pull devstral:22b
# 8 GB card — works, expect retries on complex edits
ollama pull qwen3-coder:8bFull per-tier reasoning in the model guide.
export OLLAMA_API_BASE=http://localhost:11434
aider --model ollama_chat/qwen3.6:27bThe ollama_chat/ prefix matters — it uses Ollama's chat template handling. Persist the choice in .aider.conf.yml at your repo root so plain aider picks it up:
model: ollama_chat/qwen3.6:27bAider's repo map plus file contents blow through Ollama's default context fast, and a truncated context is the #1 cause of "the model ignored half my files". Set the context explicitly:
# .aider.conf.yml
model-settings:
- name: ollama_chat/qwen3.6:27b
extra_params:
num_ctx: 16384Remember the VRAM cost: KV cache grows with context — the checker shows exactly how much headroom your card has at 16K vs 32K.
Local Aider rewards discipline: one focused change per message ("add retry logic to fetch_data and update its test"), let it commit, review the diff, continue. Use /undo (or plain git) when an edit misses. With a test suite present, aider --auto-test closes the loop — the model sees failures and iterates, which flatters local models by giving them concrete feedback instead of open-ended instructions.