Skip to content

Can Mac M2 16G run K2 Horizon 3.7B?

Comfortable: GGUF Q8_0 needs 6.2 GB at 4K, batch 1; headroom 5.8 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_M4.0ComfortableVerified file
GGUF Q8_06.2ComfortableVerified file

Context capacity · GGUF Q8_0

ContextTotal GBVerdict
4K6.2Comfortable
16K8.1Comfortable
32K10.6Tight
128K25.4Does not fit

Generation speed

GGUF Q8_0: 20 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs