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
Quant
Context
VRAM needed
Fits?
tok/s (decode)
Q4
4K
3.08 GB
Yes
41.3measured
Q4
8K default
3.4 GB
Yes
41.3measured
Q4
32K
5.32 GB
Yes
41.3measured
FP16
4K
7.72 GB
Yes
6.6est.
FP16
8K default
8.04 GB
Yes
6.6est.
FP16
32K
9.96 GB
Yes
6.6est.
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).