Local AI Advisor

Can MacBook Pro M3 Pro 36 GB run Muse Glimmer (30B)?

36 GB unified · 150 GB/s memory bandwidth · Muse Glimmer (30B) has 29.6B parameters.

Short answer

Yes, acceptable for chat; not recommended for coding in a repository.

Best quantization for chat: Q4_K_M (16 GB of weights) on LM Studio. Generation: 6–8 tok/s, leaving about 11 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 WebUIAcceptableQ4_K_M6–8 tok/s≈9 s8KDetails
Coding questionswith ContinueBorderlineQ4_K_M6–8 tok/s≈60 s16KDetails
Coding in a repositorywith AiderTechnically RunsQ4_K_M6–8 tok/s≈3 min32KDetails
Agentic codingwith OpenCodeTechnically RunsQ4_K_M6–8 tok/s≈4 min32KDetails
Long documents (64K)with Open WebUIBorderlineQ4_K_M5–7 tok/s≈13 min64KDetails

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.