← AI Hashrate

Can Mac mini M4 32GB run Llama-3.2-3B-Instruct?

Apple · 32 GB LPDDR5X · 120 GB/s bandwidth · Meta · 3.2B · model ctx up to 128K

Yes — the Mac mini M4 32GB (32 GB LPDDR5X) can run Llama-3.2-3B-Instruct. At Q4 with the default 8K context it needs ≈ 3.4 GB VRAM (weights 1.76 GB + KV cache 0.64 GB + 1 GB runtime overhead), which fits within 32 GB. Decode at Q4/8K: ≈ 41.3 tok/s (measured, batch 1). FP16 (≈ 8.04 GB) also fits, at ≈ 6.6 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

QuantContextVRAM neededFits?tok/s (decode)
Q44K3.08 GBYes41.3 measured
Q48K default3.4 GBYes41.3 measured
Q432K5.32 GBYes41.3 measured
FP164K7.72 GBYes6.6 est.
FP168K default8.04 GBYes6.6 est.
FP1632K9.96 GBYes6.6 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 32GB VRAM
Q41.76 GB0.64 GB1 GB3.4 GB32 GB
FP166.4 GB0.64 GB1 GB8.04 GB32 GB

Other GPUs that run Llama-3.2-3B-Instruct

All GPUs for Llama-3.2-3B-Instruct →

Other models for the Mac mini M4 32GB

All models on the Mac mini M4 32GB →