Apple · 32 GB LPDDR5X · 120 GB/s bandwidth ·
Alibaba · 397.0B (active 17.0B) · MoE · model ctx up to 256K
No — Qwen3.5-397B-A17B at Q4 needs ≈ 221.05 GB even at 4K context, beyond the Mac mini M4 32GB's 32 GB LPDDR5X. It would only run with heavy CPU/disk offload. FP16 needs ≈ 798.4 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
221.05 GB
No
—
Q4
8K default
222.75 GB
No
—
Q4
32K
232.95 GB
No
—
FP16
4K
796.7 GB
No
—
FP16
8K default
798.4 GB
No
—
FP16
32K
808.6 GB
No
—
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
Quant
Weights
KV cache
Overhead
Total needed
Mac mini M4 32GB VRAM
Q4
218.35 GB
3.4 GB
1 GB
222.75 GB
32 GB
FP16
794.0 GB
3.4 GB
1 GB
798.4 GB
32 GB
Other GPUs that run Qwen3.5-397B-A17B
No catalog GPU fully fits Qwen3.5-397B-A17B at Q4/8K — see the model page for offload estimates.