Skip to content

Can Mac M4 Max 36G run Muse Glimmer 30B?

Comfortable: GGUF Q4_K_M needs 17.7 GB at 4K, batch 1; headroom 9.3 GB.

Text input, FP16 KV cache, one card. Unified-memory capacity uses the GPU guide’s usable limit; negative headroom may require host offload. Speed source settings may differ from this 4K estimate.

Measured runs

No measured run for this pair. Sizing is an estimate, not a runtime test.

Quant memory at 4K

QuantTotal GBVerdictWeight sizing
GGUF Q4_K_M17.7ComfortableVerified file
GGUF Q5_K_M21.2ComfortableEstimated weights
GGUF Q6_K24.6TightEstimated weights
GGUF Q8_031.1Does not fitEstimated weights

Context capacity · GGUF Q4_K_M

ContextTotal GBVerdict
4K17.7Comfortable
16K17.8Comfortable
32K18.1Comfortable
128K19.4Comfortable

Generation speed

GGUF Q4_K_M: 16–21 tok/s · Derived range

Other model / GPU pairs