What quantization should I use for Qwen3.6-35B-A3B on a Mac mini M4 24GB?

MXFP4_MOE is the highest-quality quant that grades B or better on this hardware with llama.cpp at 8K context; the per-quant table on this page grades all 4 available quants.

Can a Mac mini M4 24GB run Qwen3.6-35B-A3B?

No. Qwen3.6-35B-A3B needs 22.8GB at MXFP4_MOE with llama.cpp and 8K context; the Mac mini M4 24GB has 24GB of unified memory (~75% GPU-addressable) (17.5GB usable) — it does not fit, even with CPU offload.

Mac mini M4 24GB · Qwen3.6-35B-A3B · MXFP4_MOE

❌ Won't fit

betaHybrid attention — KV computed as full-cache upper bound

weights 21.7 GBKV cache 0.67 GBoverhead 0.42 GBpool 17.5 GBneeds 22.8 GB — over the pool

assumes llama.cpp · batch 1 · 8K context · fp16 KV cache

No quant of this model fits cleanly on this hardware with llama-cpp at this context — a smaller model or more memory is the real fix.

$999 MSRP · as of 2026-07-11

Check price on Amazon

Affiliate link — we may earn a commission. Verdicts are computed before any link is attached.

Adjust assumptions — runtime, context, GPU count →

Every quant, graded

Mac mini M4 24GB × Qwen3.6-35B-A3B, llama.cpp, 8K context.

Quant	File size	Fit
Q8_0	36.9 GB	Won't fit
UD-Q5_K_XL	26.6 GB	Won't fit
UD-Q4_K_XL	22.4 GB	Won't fit
MXFP4_MOE	21.7 GB	Won't fit

Qwen3.6-35B-A3B on similar hardware

More models on the Mac mini M4 24GB

Verdict computed from published specs and measured GGUF file sizes — see how the math works.