Yes — Muse Glimmer 30B (30B) runs at 27 tok/s on M5 Max with 64 GB RAM using Q4_K_M quantization via MLX. First token latency is 0.4s. A capable open-source LLM with 30B parameters.
Want to run Muse Glimmer 30B faster — or step up to bigger models? Find your Mac →The LLMCheck index estimates Muse Glimmer 30B on M5 Max 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 →
| Metric | Value |
|---|---|
| Tokens per second | 27 tok/s |
| Time to first token | 0.4s |
| Quantization | Q4_K_M |
| Minimum RAM | 64 GB |
| Recommended engine | MLX |
| Parameters | 30B |
| Benchmark date | 2026-08 |
Q4_K_M 30B MLX M5 Max
The recommended engine for Muse Glimmer 30B on M5 Max is MLX. Install with pip and pull the model:
Alternatively, you can use Ollama for a simpler setup:
| Chip | Speed | First Token | Min RAM | Engine |
|---|---|---|---|---|
| M4 Max | 24 tok/s | 0.5s | 48 GB | MLX |
| M4 Pro | 10 tok/s | 0.8s | 24 GB | LM Studio |
To run Muse Glimmer 30B on M5 Max you need:
Muse Glimmer 30B needs about 64 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.
See how Muse Glimmer 30B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard