Skip to content

Can Mac M4 Pro 24G run Devstral Small 1.1 24B?

Comfortable: GGUF Q4_K_M needs 15.7 GB at 4K, batch 1; headroom 2.3 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_M15.7ComfortableVerified file
GGUF Q5_K_M18.2TightVerified file
GGUF Q6_K20.9Does not fitVerified file

Context capacity · GGUF Q4_K_M

ContextTotal GBVerdict
4K15.7Comfortable
16K17.7Tight
32K20.5Does not fit
128K37.0Does not fit

Generation speed

GGUF Q4_K_M: 13–17 tok/s · Derived range

Other model / GPU pairs