Skip to content

Can Mac M1 8G run Gemma 4 E4B IT?

Tight: GGUF Q4_K_M needs 5.3 GB at 4K, batch 1; headroom 0.7 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_M5.3TightVerified file
GGUF Q8_08.7Does not fitVerified file

Context capacity · GGUF Q4_K_M

ContextTotal GBVerdict
4K5.3Tight
16K5.5Tight
32K5.8Tight
128K7.5Does not fit

Generation speed

GGUF Q4_K_M: 11–14 tok/s · Derived range

Other model / GPU pairs