Skip to content

Muse Glimmer 30B on Mac mini M4 32 GB: VRAM, speed and fit

Muse Glimmer 30B at 4-bit runs on the M4 32 GB with 128K of context at about 5.6 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M4 32 GB · 4-bit (Q4_K_M) · Ollama / LM Studio · Chat

GPU memory
30.0 GB
of 32.0 GB
Context
128K
auto
Speed
5.6 tok/s
Slow
First reply
39 s
2K prompt

Where the memory goes

Model
16.8 GB
Context
1.7 GB
Overhead
859 MB
OS
10.7 GB
Free
2.0 GB
Memory
30.0 GB of 32.0 GB
Context
128K tokens · auto
Speed
5.6 tok/s · slow
First reply
39 s for a 2K prompt
Running cost
$0.85/mo at home · $30/mo on a cloud RTX A4500

Validation: Not validated

What Muse Glimmer 30B on Mac mini M4 32 GB was checked against
CheckTargetResultStatus
Fits in GPU memory21.3 GB usable19.4 GB neededPass
Headroom5% free2.0 GB free (9%)Pass
Context for chat16K or more128KPass
Writing speed15 tok/s or more5.6 tok/sFails
First replyunder 3 s, 2K prompt39 sFails

Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.

The setup

Model
Muse Glimmer 30B
Parameters
29.8B
Precision
4-bit (Q4_K_M)
Context
128K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M4 32 GB
GPU can use
21.3 GB of 32.0 GB

Running cost

At home
$0.85/mo
39 W at the wall
Renting instead
$30/mo
RTX A4500 at $0.25/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.

How to run it

Ollama
ollama run muse-glimmer:30b
llama.cpp
llama-server -hf unsloth/Muse-Glimmer-30B-GGUF
vLLM
vllm serve meta-models/Muse-Glimmer-30B
MLX (Mac)
mlx_lm.chat --model mlx-community/Muse-Glimmer-30B-4bit

Muse Glimmer 30B on similar machines

All machines: Muse Glimmer 30B VRAM requirements. Everything that runs here: what can the Mac mini M4 32 GB run?

Other models that run on Mac mini M4 32 GB

Questions

Can Muse Glimmer 30B run on Mac mini M4 32 GB?

Muse Glimmer 30B at 4-bit runs on the M4 32 GB with 128K of context at about 5.6 tokens a second.

Report VR-1YUIO0W, calculated Nov 22, 2026 from published specs, not benchmarked.