Apple · 192 GB LPDDR5 · 800 GB/s bandwidth ·
StepFun · 196.8B (active 11.0B) · MoE · model ctx up to 256K
Yes — the Mac Studio M2 Ultra 192GB (192 GB LPDDR5) 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 192 GB. Decode at Q4/8K: ≈ 46.3 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
46.3est.
Q4
8K default
111.44 GB
Yes
46.3est.
Q4
32K
118.04 GB
Yes
46.3est.
FP16
4K
395.7 GB
No
8.6est.
FP16
8K default
396.8 GB
No
8.5est.
FP16
32K
403.4 GB
No
8.2est.
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).