Apple · 64 GB LPDDR5X · 273 GB/s bandwidth ·
OpenAI · 120.4B (active 5.1B) · MoE · model ctx up to 128K
No — gpt-oss-120b at Q4 needs ≈ 67.73 GB even at 4K context, beyond the Mac mini M4 Pro 64GB's 64 GB LPDDR5X. It would only run with heavy CPU/disk offload. Decode at Q4/8K: ≈ 85.6 tok/s (estimated, batch 1). FP16 needs ≈ 242.82 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
67.73 GB
No
86.9est.
Q4
8K default
68.24 GB
No
85.6est.
Q4
32K
71.3 GB
No
78.4est.
FP16
4K
242.31 GB
No
1.9est.
FP16
8K default
242.82 GB
No
1.9est.
FP16
32K
245.88 GB
No
1.8est.
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).