Apple · 128 GB LPDDR5 · 400 GB/s bandwidth ·
Alibaba · 8.2B · model ctx up to 128K
Yes — the MacBook Pro M3 Max 128GB (128 GB LPDDR5) can run Qwen3-8B. At Q4 with the default 8K context it needs ≈ 7.15 GB VRAM (weights 4.51 GB + KV cache 1.64 GB + 1 GB runtime overhead), which fits within 128 GB. Decode at Q4/8K: ≈ 31.0 tok/s (estimated, batch 1). FP16 (≈ 19.04 GB) also fits, at ≈ 8.5 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
6.33 GB
Yes
31.0est.
Q4
8K default
7.15 GB
Yes
31.0est.
Q4
32K
12.07 GB
Yes
31.0est.
FP16
4K
18.22 GB
Yes
8.5est.
FP16
8K default
19.04 GB
Yes
8.5est.
FP16
32K
23.96 GB
Yes
8.5est.
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).