Skip to content

Can Mac M5 Ultra 256G run Laguna S 2.1 118B-A8B?

Comfortable: GGUF Q8_0 needs 130.9 GB at 4K, batch 1; headroom 61.1 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_M71.0ComfortableVerified file
GGUF Q8_0130.9ComfortableVerified file

Context capacity · GGUF Q8_0

ContextTotal GBVerdict
4K130.9Comfortable
16K131.6Comfortable
32K132.4Comfortable
128K137.3Comfortable

Generation speed

GGUF Q8_0: 149 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs