Apple · 32 GB LPDDR5X · 120 GB/s bandwidth ·
Mistral · 23.6B · model ctx up to 128K
Yes — the Mac mini M4 32GB (32 GB LPDDR5X) can run Devstral-Small-2507. At Q4 with the default 8K context it needs ≈ 18.7 GB VRAM (weights 12.98 GB + KV cache 4.72 GB + 1 GB runtime overhead), which fits within 32 GB. Decode at Q4/8K: ≈ 3.2 tok/s (estimated, batch 1). FP16 needs ≈ 52.92 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
16.34 GB
Yes
3.2est.
Q4
8K default
18.7 GB
Yes
3.2est.
Q4
32K
32.86 GB
No
8.8est.
FP16
4K
50.56 GB
No
1.0est.
FP16
8K default
52.92 GB
No
0.9est.
FP16
32K
67.08 GB
No
0.6est.
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).