Which local coding model actually fits your machine
· updated
Running models locally is free and private, and it is the part of Adrian that needs no account and no card. The awkward question is which model to actually pull. Model pages advertise parameter counts; what decides whether something runs on your laptop is memory.
Adrian ships a curated catalog rather than pointing you at the whole of Ollama, and every entry carries a download size and a minimum RAM figure. The groupings below come from that catalog.
8GB — small models, real but limited
At 8GB you are working with models between roughly 1B and 4B parameters. They are genuinely useful for scaffolding a component, renaming things coherently, or drafting a small utility. They are not going to carry a multi-file feature on their own.
- Qwen2.5 Coder 1.5B — 1.1GB, the lightest coding model in the catalog.
- Gemma 3 1B and Gemma 3 4B — 0.9GB and 3.3GB.
- Llama 3.2 1B and 3B, Phi-3 Mini, Qwen2.5 3B — all under 2.5GB.
12–16GB — the practical sweet spot
This is where local coding stops feeling like a demo. 7B-class coding models fit comfortably, and at 16GB a few genuinely strong 20B-class models come into range.
- Qwen2.5 Coder 7B — 4.7GB, 12GB RAM.
- DeepSeek Coder 6.7B — 4GB, 12GB RAM.
- Ornith 1.5 9B — 6.6GB, 12GB RAM, tuned for tool use and multi-step coding.
- Codestral 22B and GPT-OSS 20B — 13GB each, 16GB RAM.
24–32GB — large models on one machine
- Qwen3 Coder 30B A3B — 18GB, 24GB RAM.
- Devstral Small 24B — 14GB, 24GB RAM.
- Qwen2.5 Coder 32B — 20GB, 32GB RAM.
128GB and up
The catalog does list frontier-scale local models — DeepSeek R1 671B, Kimi K2.6, GLM-5.1, Qwen3 Coder 480B. These want 128GB of RAM or more and hundreds of gigabytes of disk. They are there for workstations, not laptops.
The honest part
Structure closes some of the gap. Adrian wraps whatever model you choose in planning, tool use, self-review and a compile check, which is why a 7B model inside a build system beats a 7B model answering in a chat box. It does not close the gap entirely. A small local model supervised by a real pipeline is a good free option, not a secret equal of a frontier model.
If your machine is on the lower end, the other free route is bringing your own API key — you pay your provider directly and Adrian takes no cut of that bill. The hosted plans exist for when you would rather not manage either.