Apple · 128 GB LPDDR5X · 546 GB/s bandwidth ·
Alibaba · 32.8B · model ctx up to 128K
Yes — the MacBook Pro M4 Max 128GB (128 GB LPDDR5X) can run Qwen3-32B. At Q4 with the default 8K context it needs ≈ 25.6 GB VRAM (weights 18.04 GB + KV cache 6.56 GB + 1 GB runtime overhead), which fits within 128 GB. Decode at Q4/8K: ≈ 10.6 tok/s (estimated, batch 1). FP16 (≈ 73.16 GB) also fits, at ≈ 2.9 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
22.32 GB
Yes
10.6est.
Q4
8K default
25.6 GB
Yes
10.6est.
Q4
32K
45.28 GB
Yes
10.6est.
FP16
4K
69.88 GB
Yes
2.9est.
FP16
8K default
73.16 GB
Yes
2.9est.
FP16
32K
92.84 GB
Yes
2.9est.
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).