What can I realistically do with local AI on a Mac mini M5 Pro (48GB)?
Post · https://lobste.rs/s/umsitb
I just got a Mac mini with an M5 Pro (base CPU config) and 48GB of unified memory. I want to run as much AI locally as makes sense, but it's hard to separate what actually works day to day from benchmark hype. What I'd like to do: - Coding: autocomplete and agentic workflows with local models - Image generation - Anything else genuinely useful: transcription, RAG over my notes, etc. Questions: 1. Which models and quantizations fit comfortably in 48GB and are actually usable, not just "it runs"? 2. Which runtime and tools: MLX, llama.cpp, Ollama, LM Studio, ComfyUI, something else? 3. What's your setup, and what did you give up on and go back to cloud APIs for? Real tokens/sec numbers and "this was a waste of time" stories are especially welcome.
First seen by Oriel on .
AI summary
A Mac mini M5 Pro owner asks what local AI workflows are realistically useful with 48GB of unified memory, seeking practical model, runtime, and performance advice.
- The desired uses include local coding autocomplete and agentic workflows, image generation, transcription, and retrieval-augmented generation over personal notes.
- The author asks which models and quantizations fit comfortably in 48GB and are usable in daily work.
- They compare potential runtimes and tools including MLX, llama.cpp, Ollama, LM Studio, and ComfyUI.
- The discussion seeks real tokens-per-second measurements and examples of local workflows abandoned in favor of cloud APIs.
#local ai #apple silicon #llm inference #image generation
Generated by gpt-5.6-sol. Check the original for details.
Metric trends
Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained
Points
Score reported by the source.
- Lobsters: 24, latest observation ; +23 over observed period since
Comments
Comment count reported by the source.
- Lobsters: 11, latest observation ; +11 over observed period since
Aliases
| Source | External ID | URL |
|---|---|---|
| Lobsters | umsitb | https://lobste.rs/s/umsitb/what_can_i_realistically_do_with_local_ai Read discussion |