Skip to content

Can Mac M4 Pro 48G run K2 Horizon 32B?

Comfortable: GGUF Q6_K needs 30.9 GB at 4K, batch 1; headroom 5.1 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_M23.1ComfortableVerified file
GGUF Q5_K_M26.9ComfortableVerified file
GGUF Q6_K30.9ComfortableVerified file
GGUF Q8_039.7Does not fitVerified file

Context capacity · GGUF Q6_K

ContextTotal GBVerdict
4K30.9Comfortable
16K34.2Tight
32K38.6Does not fit
128K65.0Does not fit

Generation speed

GGUF Q6_K: 10 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs