Skip to content

Can Mac M1 8G run K2 Horizon 3.7B?

Comfortable: GGUF Q4_K_M needs 4.0 GB at 4K, batch 1; headroom 2.0 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_06.2TightVerified file

Context capacity · GGUF Q4_K_M

ContextTotal GBVerdict
4K4.0Comfortable
16K5.9Tight
32K8.3Does not fit
128K23.2Does not fit

Generation speed

GGUF Q4_K_M: 22 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs