Skip to content

Can Mac M5 Pro 64G run GLM-4.7-Flash?

Comfortable: GGUF Q8_0 needs 33.5 GB at 4K, batch 1; headroom 14.5 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_M19.5ComfortableVerified file
GGUF Q8_033.5ComfortableVerified file

Context capacity · GGUF Q8_0

ContextTotal GBVerdict
4K33.5Comfortable
16K34.2Comfortable
32K35.1Comfortable
128K40.6Comfortable

Generation speed

GGUF Q8_0: 101 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs