Can you run Ollama on a 16 GB Mac?
By Junaid, maker of Taskglass · Updated
Yes. On a 16 GB Apple Silicon Mac, 7–8B models at 4-bit quantization (about 5 GB) run well alongside normal apps, 12–14B models (about 8–9 GB) fit if you close heavy apps, and 30B and larger models don't fit. Ollama keeps a model in memory for a few minutes after use; ollama stop frees it right away.
How to run Ollama well on 16 GB
- 1
Pick a model that fits
Choose a 7–8B model for everyday use. The model's download size is a good guide to the memory it needs, plus some extra for the conversation (context).
- 2
Check where it runs
While the model is loaded, ollama ps shows its size and whether it runs fully on the GPU. If part of it falls back to the CPU, it's too big for comfort: use a smaller model.
- 3
Keep the context reasonable
Longer context windows use more memory on top of the model. Very large context settings can push a model that fit into swapping.
- 4
Free the memory when you're done
ollama stop <model> unloads it immediately. By default Ollama unloads a model after about 5 minutes idle; the OLLAMA_KEEP_ALIVE setting changes that.
Model sizes on a 16 GB Mac (4-bit)
| Model size | Memory | On 16 GB |
|---|---|---|
| 1–4B | 1–3 GB | Runs easily |
| 7–8B | about 5 GB | Runs well with your apps open |
| 12–14B | about 8–9 GB | Fits if you close heavy apps |
| 30–32B | about 18–20 GB | Doesn't fit |
| 70B | about 40 GB | Doesn't fit |
Why is Ollama slow on my Mac?
Usually the model is too big for your memory, so part of it runs on the CPU or macOS swaps. ollama ps shows the CPU/GPU split; a smaller model or closing heavy apps fixes it.
Does Ollama use the GPU on Apple Silicon?
Yes, through Metal. Apple Silicon shares one pool of memory between CPU and GPU, and by default macOS lets the GPU use only part of it, which is why a model close to your total RAM won't fit.
Can I run Ollama on an 8 GB Mac?
Small models (1–4B) run; 7–8B models are tight and will swap with other apps open.
How Taskglass helps
Taskglass's Agents tab shows Ollama and LM Studio with the memory their loaded model holds, whether they're busy or idle, and flags a model sitting idle in memory in its diagnosis.
See how it worksQuestions
How much RAM does Llama 3.1 8B need?
About 5 GB at the default 4-bit quantization, plus a little more for context.
How do I unload a model in Ollama?
Run ollama stop <model>. ollama ps lists the models currently loaded.
Is 16 GB enough for local AI and coding at the same time?
With a 7–8B model, yes, for most setups. Add Docker or simulators and 24–32 GB is more comfortable.
Processes you might see
- OllamaRuns AI language models locally on your Mac.
- python3 (Python)The Python programming language running a script, tool or app on your Mac.
- kernel_taskThe core of macOS itself. It also holds busy apps back on purpose to stop your Mac overheating.
- node (Node.js)Node.js, the JavaScript runtime used by developer tools, local servers and some apps.
More guides
- Why is my Mac so slow?
- Why is my Mac so hot?
- Why is my Mac fan so loud?
- What's draining my MacBook battery?
- Task Manager on Mac: how to see and close running apps
- How to ask Claude why your Mac is slow
- Is Claude Code slowing down your Mac?
- What is System Data on Mac, and how do I reduce it?
- How to free up disk space on a developer Mac
- How much RAM do I need on a Mac for coding?