Local AI Advisor

Can Mac mini M4 24 GB run Muse Glimmer (30B)?

24 GB unified · 120 GB/s memory bandwidth · Muse Glimmer (30B) has 29.6B parameters.

Short answer

It loads, but it's borderline even for chat.

Best quantization for chat: Q4_K_M (16 GB of weights) on LM Studio. Generation: 4.4–6 tok/s, leaving about 0.0 GB free for your other apps.

How it rates for each workload

Same model and machine, different jobs. Agents and long documents send far bigger prompts than chat, so they need much more speed and memory.

WorkloadVerdictQuantGenerationFirst replyContext
Chatwith Open WebUIBorderlineQ4_K_M4.4–6 tok/s≈15 s8KDetails
Coding questionswith ContinueDoes Not Fit————Details
Coding in a repositorywith AiderDoes Not Fit————Details
Agentic codingwith OpenCodeDoes Not Fit————Details
Long documents (64K)with Open WebUIDoes Not Fit————Details

Speeds are estimates calibrated against measured benchmarks on similar hardware. “First reply” is the time to read the workload’s opening prompt. How we calculate

Different tool, context size or workload?

These pages use typical settings. The full check models your exact setup.