Skip to content

Can Mac M4 Max 36G run Granite 4.2 30B?

Comfortable: GGUF Q5_K_M needs 22.8 GB at 4K, batch 1; headroom 4.2 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_M19.6ComfortableVerified file
GGUF Q5_K_M22.8ComfortableVerified file
GGUF Q6_K26.2TightVerified file
GGUF Q8_033.6Does not fitVerified file

Context capacity · GGUF Q5_K_M

ContextTotal GBVerdict
4K22.8Comfortable
16K26.1Tight
32K30.5Does not fit
128K56.9Does not fit

Generation speed

GGUF Q5_K_M: 13–17 tok/s · Derived range

Other model / GPU pairs