Run Muse Glimmer 30B on M6

Yes — Muse Glimmer 30B (30B) runs at 8 tok/s on M6 with 32 GB RAM using Q4_K_M quantization via MLX. First token latency is Nones. A capable open-source LLM with 30B parameters.

Speed
estimated8
tok/s
First Token
estimatedNone
seconds
RAM Needed
32
GB minimum
Engine
MLX
recommended
Want to run Muse Glimmer 30B faster — or step up to bigger models? Find your Mac →

Benchmark Details

The LLMCheck index estimates Muse Glimmer 30B on M6 using our published methodology: Q4_K_M quantization, memory-bandwidth scaling, and cross-referenced third-party benchmarks where available. Figures are transparent estimates — own this config? Submit a real benchmark →

MetricValue
Tokens per second8 tok/s
Time to first tokenNones
QuantizationQ4_K_M
Minimum RAM32 GB
Recommended engineMLX
Parameters30B
Benchmark date2026-08

Q4_K_M 30B MLX M6

Setup Guide: Run Muse Glimmer 30B on M6

The recommended engine for Muse Glimmer 30B on M6 is MLX. Install with pip and pull the model:

pip install mlx-lm
mlx_lm.generate --model mlx-community/muse-glimmer-30b-q4_k_m --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run muse-glimmer-30b

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M5 Max 27 tok/s 0.4s 64 GB MLX
M4 Max 24 tok/s 0.5s 48 GB MLX
M4 Pro 10 tok/s 0.8s 24 GB LM Studio

System Requirements

To run Muse Glimmer 30B on M6 you need:

🛒 Get a Mac that runs Muse Glimmer 30B

Muse Glimmer 30B needs about 32 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:

As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep our benchmarks free.

Compare More Models

See how Muse Glimmer 30B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard