Skip to content

Can Mac M5 Pro 64G run Qwen3.6 27B?

Comfortable: GGUF Q8_0 needs 30.7 GB at 4K, batch 1; headroom 17.3 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_M19.1ComfortableVerified file
GGUF Q5_K_M22.2ComfortableVerified file
GGUF Q8_030.7ComfortableVerified file

Context capacity · GGUF Q8_0

ContextTotal GBVerdict
4K30.7Comfortable
16K31.5Comfortable
32K32.6Comfortable
128K39.2Comfortable

Generation speed

GGUF Q8_0: 11 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs