Can Mac Studio M2 Ultra 128 GB run Muse Glimmer (30B)?

128 GB unified · 800 GB/s memory bandwidth · Muse Glimmer (30B) has 29.6B parameters.

Short answer

Yes, excellent for chat and acceptable or better for every workload we test.

Best quantization for chat: Q4_K_M (16 GB of weights) on LM Studio. Generation: 20–25 tok/s, leaving about 101 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.

Workload	Verdict	Quant	Generation	First reply	Context
Chatwith Open WebUI	Excellent	Q4_K_M	20–25 tok/s	≈3 s	8K	Details
Coding questionswith Continue	Comfortable	Q4_K_M	20–25 tok/s	≈15 s	16K	Details
Coding in a repositorywith Aider	Acceptable	Q4_K_M	19–25 tok/s	≈45 s	32K	Details
Agentic codingwith OpenCode	Acceptable	Q4_K_M	19–25 tok/s	≈65 s	32K	Details
Long documents (64K)with Open WebUI	Acceptable	Q4_K_M	19–25 tok/s	≈3 min	64K	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

Other models for Mac Studio M2 Ultra 128 GB

The best-rated models for chat on this machine.

Everything Mac Studio M2 Ultra 128 GB can run

Cheapest machines for Muse Glimmer (30B)

Hardware rated comfortable or better for chat, lowest price first.

Same chip, other memory: 64 GB, 192 GB

Different tool, context size or workload?

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

Open sourceCheck my exact setup