Apple · 128 GB LPDDR5X · 546 GB/s bandwidth ·
StepFun · 196.8B (active 11.0B) · MoE · model ctx up to 256K
Yes — the MacBook Pro M4 Max 128GB (128 GB LPDDR5X) can run Step-3.5-Flash. At Q4 with the default 8K context it needs ≈ 111.44 GB VRAM (weights 108.24 GB + KV cache 2.2 GB + 1 GB runtime overhead), which fits within 128 GB. Decode at Q4/8K: ≈ 31.6 tok/s (estimated, batch 1). FP16 needs ≈ 396.8 GB — does not fit on this card. 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
110.34 GB
Yes
31.6est.
Q4
8K default
111.44 GB
Yes
31.6est.
Q4
32K
118.04 GB
Yes
31.6est.
FP16
4K
395.7 GB
No
2.6est.
FP16
8K default
396.8 GB
No
2.6est.
FP16
32K
403.4 GB
No
2.5est.
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).