Skip to content

Can Mac M4 24G run Gemma 4 26B-A4B IT?

Tight: GGUF Q4_K_M needs 18.2 GB at 4K, batch 1; headroom -0.2 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_M18.2TightVerified file
GGUF Q8_028.5Does not fitVerified file

Context capacity · GGUF Q4_K_M

ContextTotal GBVerdict
4K18.2Tight
16K18.5Tight
32K18.8Tight
128K20.9Does not fit

Generation speed

GGUF Q4_K_M: 47 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs