Skip to content

Can Mac M3 Pro 36G run Apex 35B V1.0?

Comfortable: GGUF Q3_K_M needs 18.7 GB at 4K, batch 1; headroom 8.3 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 Q3_K_M18.7ComfortableVerified file
GGUF Q4_K_M23.9TightVerified file
GGUF Q5_K_M28.8Does not fitVerified file
GGUF Q8_039.6Does not fitVerified file

Context capacity · GGUF Q3_K_M

ContextTotal GBVerdict
4K18.7Comfortable
16K19.0Comfortable
32K19.3Comfortable
128K21.4Comfortable

Generation speed

GGUF Q3_K_M: 105 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs