← AI Hashrate

Can MacBook Pro M3 Max 128GB run gemma-3-12b-it?

Apple · 128 GB LPDDR5 · 400 GB/s bandwidth · Google · 12.2B · model ctx up to 128K

Yes — the MacBook Pro M3 Max 128GB (128 GB LPDDR5) can run gemma-3-12b-it. At Q4 with the default 8K context it needs ≈ 10.11 GB VRAM (weights 6.71 GB + KV cache 2.4 GB + 1 GB runtime overhead), which fits within 128 GB. Decode at Q4/8K: ≈ 21.2 tok/s (estimated, batch 1). FP16 (≈ 27.8 GB) also fits, at ≈ 5.8 tok/s (estimated). Estimates come from memory-bandwidth math; rows tagged measured override estimates. Relative ranking is more reliable than absolute tok/s. Methodology.

Fit & speed by quant and context

QuantContextVRAM neededFits?tok/s (decode)
Q44K8.91 GBYes21.2 est.
Q48K default10.11 GBYes21.2 est.
Q432K17.31 GBYes21.2 est.
FP164K26.6 GBYes5.8 est.
FP168K default27.8 GBYes5.8 est.
FP1632K35.0 GBYes5.8 est.

Fits = weights + KV(ctx) + 1 GB overhead ≤ 95% of VRAM. Measured anchors are context-agnostic; the fit verdict is recomputed per context. A missing tok/s means the model is far beyond this card (offload-only territory).

VRAM breakdown at 8K context

QuantWeightsKV cacheOverheadTotal neededMacBook Pro M3 Max 128GB VRAM
Q46.71 GB2.4 GB1 GB10.11 GB128 GB
FP1624.4 GB2.4 GB1 GB27.8 GB128 GB

Other GPUs that run gemma-3-12b-it

All GPUs for gemma-3-12b-it →

Other models for the MacBook Pro M3 Max 128GB

All models on the MacBook Pro M3 Max 128GB →