Skip to content

Can Mac M4 Pro 24G run Xing4.0 29B-A4B?

Comfortable: GGUF IQ3_XXS needs 15.3 GB at 4K, batch 1; headroom 2.7 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 Q8_034.9Does not fitVerified file
GGUF Q6_K28.6Does not fitVerified file
GGUF Q5_K_M25.3Does not fitVerified file
GGUF Q4_K_M21.2Does not fitVerified file
GGUF IQ4_XS19.0Does not fitVerified file
GGUF Q3_K_M17.0TightVerified file
GGUF IQ3_XXS15.3ComfortableVerified file
GGUF Q2_K13.6ComfortableVerified file
GGUF IQ2_XXS11.0ComfortableVerified file

Context capacity · GGUF IQ3_XXS

ContextTotal GBVerdict
4K15.3Comfortable
16K15.9Tight
32K16.6Tight
128K21.3Does not fit

Generation speed

GGUF IQ3_XXS: 155 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs