Skip to content

Can Mac M3 Max 128G run North Mini Code 1.0 30B-A3B?

Comfortable: GGUF Q8_0 needs 34.3 GB at 4K, batch 1; headroom 61.7 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 Q3_K_M15.3ComfortableVerified file
GGUF Q4_K_M20.0ComfortableVerified file
GGUF Q8_034.3ComfortableVerified file

Context capacity · GGUF Q8_0

ContextTotal GBVerdict
4K34.3Comfortable
16K34.7Comfortable
32K35.1Comfortable
128K37.8Comfortable

Generation speed

GGUF Q8_0: 132 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs