← AI Hashrate

Can Mac mini M4 Pro 64GB run gpt-oss-120b?

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

QuantContextVRAM neededFits?tok/s (decode)
Q44K67.73 GBNo86.9 est.
Q48K default68.24 GBNo85.6 est.
Q432K71.3 GBNo78.4 est.
FP164K242.31 GBNo1.9 est.
FP168K default242.82 GBNo1.9 est.
FP1632K245.88 GBNo1.8 est.

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).

VRAM breakdown at 8K context

QuantWeightsKV cacheOverheadTotal neededMac mini M4 Pro 64GB VRAM
Q466.22 GB1.02 GB1 GB68.24 GB64 GB
FP16240.8 GB1.02 GB1 GB242.82 GB64 GB

Other GPUs that run gpt-oss-120b

All GPUs for gpt-oss-120b →

Other models for the Mac mini M4 Pro 64GB

All models on the Mac mini M4 Pro 64GB →