# On a Mac or a laptop > Run decisio on a Mac with Apple silicon from an MLX build, sized to your Mac's memory, or on any 16 GB laptop with Ollama. Source: https://opendecisio.com/docs/deploy/mac/ On a 64 GB Mac, install it and start the default model, Gemma 4 31B. ``` git clone --branch v0.19.0 https://github.com/aminry/decisio cd decisio uv sync --extra mlx ``` Shown, not run: it needs a Mac with Apple silicon, which this check does not have. ``` uv run python -m decisio.serve.vllm_engine --backend mlx --base gemma-4-31b --model mlx-community/gemma-4-31b-it-6bit ``` Needs a Mac with Apple silicon: taken as it is from decisio's checked docs, [run record](https://github.com/aminry/decisio/tree/v0.19.0/runs/2026-10-07_mlx-gemma-31b). [Figure: Each build against the Mac it is for, at its peak on the longest text it serves; only the 64 GB Mac was measured. 64 GB Mac, Gemma 4 31B, 6-bit: 24.9 GB of weights, 31.1 GB at its peak at about 16k tokens, its longest. 48 GB Mac, Gemma 4 31B, 4-bit: 19.2 GB of weights, 25.3 GB at its peak at about 16k tokens, its longest, read on 64 GB. 32 GB Mac, Gemma 4 12B, 6-bit: 9.7 GB of weights, 15.1 GB at its peak at 32,687 tokens. 16 GB Mac, Gemma 4 12B on Ollama: 8.6 GB at its peak in Ollama, at 8,192 tokens, read on 64 GB.] ## 1 Pick the build for your Mac | Your Mac | Model and build | Memory: weights, then peak | Texts up to | One [question](https://opendecisio.com/docs/glossary/#question) on a new text | | --- | --- | --- | --- | --- | | 64 GB | Gemma 4 31B, 6-bit | 24.9 GB; 29.6, 31.1 and 33.7 GB at about 8k, 16k and 32k tokens | 16,383 tokens | not measured | | 48 GB | Gemma 4 31B, 4-bit | 19.2 GB; 23.9, 25.3 and 28.0 GB, read on a 64 GB Mac | 16,383 tokens | 9.4 s at 3,000 tokens, on a busy Mac | | 32 GB | Gemma 4 12B, 6-bit | 9.7 GB; 15.1 GB at 32,687 tokens | 32,768 tokens | 1,312 ms at 1,000 tokens | | A 16 GB laptop | Gemma 4 12B on Ollama | a 7.7 GB download; 8.6 GB in Ollama, read on a 64 GB Mac | 8,192 tokens | not recorded | Measured on one Apple M5 Pro with 64 GB; no smaller Mac was measured, and GB are 10⁹ bytes. The Qwen base runs from its 6-bit build too; its 4-bit build is for Macs with more than 32 GB. ## 2 Start it On a 64 GB Mac, the command above starts the 31B. On a smaller Mac, start the build that fits it instead: 48 GB `--revision v0.15.0` serves the build that was measured, whatever its repository holds later. ``` uv run python -m decisio.serve.vllm_engine --backend mlx --base gemma-4-31b --model tachara-ai/decisio-gemma-4-31b-mlx-4bit --revision v0.15.0 ``` Needs a Mac with Apple silicon: taken as it is from decisio's checked docs, [run record](https://github.com/aminry/decisio/tree/v0.19.0/runs/2026-10-16_mlx-gemma-31b-4bit). 32 GB ``` uv run python -m decisio.serve.vllm_engine --backend mlx --base gemma-4-12b --model mlx-community/gemma-4-12B-it-6bit ``` Needs a Mac with Apple silicon: taken as it is from decisio's checked docs, [run record](https://github.com/aminry/decisio/tree/v0.19.0/runs/2026-10-05_mlx-gemma). ## 3 Mind the memory - The server sets MLX’s memory limits itself before it loads the model, and prints them in a start-up line that begins `MLX MEMORY`. - When the model cannot fit, it refuses to start, with the numbers, instead of freezing the Mac: ``` decisio: the gemma-4-12b base needs about 16.6 GiB under MLX (9.1 GiB of weights, a working set of 5.6 GiB at a 32k-token state, and the MLX cache limit of 2.0 GiB), which is more than the memory limit of 14.0 GiB (--mlx-memory-limit-gb 14). Raise the limit, lower --mlx-cache-limit-gb, or start a smaller base ``` Recorded output. - Run one model server on a Mac at a time: two servers can each stay under their own limit and still add up to more than the Mac has. - `/health` reports the memory under `memory`; watch `physical_footprint_bytes`, the figure Activity Monitor shows, not the resident size. ## 4 What a Mac does not serve - Images in a question, adapters (`--adapter`), packed mode, or the [intent head](https://opendecisio.com/docs/glossary/#intent-head) on a second engine (`--head-engine`). - FP8 checkpoints: a Mac always names an MLX build with `--model`. - Teaching a [task](https://opendecisio.com/docs/glossary/#task) works, slowly: on the 31B 4-bit, about an hour for 770 labelled examples (77 [options](https://opendecisio.com/docs/glossary/#option)) and about 2.6 hours for 1,500 (150 options). ## On a laptop, with Ollama Ollama runs decisio’s Gemma 4 12B listing on Mac, Linux or Windows, and its smallest tag fits a 16 GB laptop. You need Ollama 0.35.1 or later. ``` # the Gemma 4 12B base, for 16 GB laptops ollama pull aminroudaki/decisio-gemma # the Qwen base ollama pull aminroudaki/decisio ``` Run against Ollama 0.35.1 with aminroudaki/decisio-gemma and aminroudaki/decisio, the listing as published, on 2026-10-09; the answers are Ollama's, not the default model's on a decisio server. Its comments are shown above their commands. | Tag | Download | In Ollama | | --- | --- | --- | | `q4_k_m`, also `latest` | 7.7 GB | 8.6 GB, at the listing’s 8,192-token context | | `q8_0` | not given | 13.6 GB | The Qwen listing’s smallest tag is a 23 GB download, so it needs a machine with more memory. Then ask it a question on Ollama’s decision route, on port 11434, with the listing named in `model`: ``` curl http://localhost:11434/v1/systemone \ -H 'Content-Type: application/json' \ -d '{ "model": "aminroudaki/decisio-gemma", "state": "Hi, since this morning none of our 40 staff can log in to the dashboard. We get \"session expired\" right after entering the password. Payroll is due today.", "questions": { "urgent": { "type": "noul", "instructions": "Does this ticket need a response within the hour?" }, "category": { "type": "choice", "instructions": "Which team should handle this ticket?", "criteria": { "billing": "Invoices, payments, refunds", "access": "Login, passwords, permissions", "bug": "The product behaves wrongly", "other": null } }, "impact": { "type": "score", "instructions": "Rate the business impact using only the reported facts.", "criteria": [ "No function impaired", "One user impaired, with a workaround", "Many users blocked from a core function", "Data loss or legal exposure" ] } } }' ``` Run against Ollama 0.35.1 with aminroudaki/decisio-gemma, the listing as published, on 2026-10-09; the answers are Ollama's, not the default model's on a decisio server. Ollama builds its own prompt and applies none of decisio’s corrections to the [probabilities](https://opendecisio.com/docs/glossary/#probability), so they are not decisio’s measured ones. To teach and certify tasks, run a decisio server. ## What next - [Get started](https://opendecisio.com/docs/#3-ask-your-first-question): send your first question and read the answer. - [Requirements and limits](https://opendecisio.com/docs/limits/): every machine, the context length and what was measured on what. - [Teach a task](https://opendecisio.com/docs/tasks/): teach a question you ask again and again, and certify its answers.