Apple · 128 GB LPDDR5 · 400 GB/s bandwidth ·
Google · 4.3B · model ctx up to 128K
Yes — the MacBook Pro M3 Max 128GB (128 GB LPDDR5) can run gemma-3-4b-it. At Q4 with the default 8K context it needs ≈ 4.15 GB VRAM (weights 2.37 GB + KV cache 0.78 GB + 1 GB runtime overhead), which fits within 128 GB. Decode at Q4/8K: ≈ 65.3 tok/s (estimated, batch 1). FP16 (≈ 10.38 GB) also fits, at ≈ 17.9 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
Quant
Context
VRAM needed
Fits?
tok/s (decode)
Q4
4K
3.76 GB
Yes
65.3est.
Q4
8K default
4.15 GB
Yes
65.3est.
Q4
32K
6.49 GB
Yes
65.3est.
FP16
4K
9.99 GB
Yes
17.9est.
FP16
8K default
10.38 GB
Yes
17.9est.
FP16
32K
12.72 GB
Yes
17.9est.
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).