Skip to content

Can Mac M2 Max 96G run Laguna S 2.1 118B-A8B?

Tight: GGUF Q4_K_M needs 71.0 GB at 4K, batch 1; headroom 1.0 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_M71.0TightVerified file
GGUF Q8_0130.9Does not fitVerified file

Context capacity · GGUF Q4_K_M

ContextTotal GBVerdict
4K71.0Tight
16K71.6Tight
32K72.5Tight
128K77.4Does not fit

Generation speed

GGUF Q4_K_M: 92 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs