No — not on this device

Qwen3 30B-A3B at Q4_K_M needs 18.5 GB against 18.0 GB usable, and the shortfall of 0.5 GB is more than 64 GB of system RAM can cover at a tolerable speed. A smaller sibling or a lower quantisation is the honest answer here.

Does not fit 8K context Q4_K_M · 17.1 GB Apache 2.0 Released Apr 2025

The MoE that made "3B active" a category. Qwen3.6 35B-A3B is its direct replacement.

What hardware do I need for Qwen3 30B-A3B? →

Fits instead: Qwen3 14B (10.2 GB) · Qwen3 8B (6.3 GB)

The VRAM budget

weights 17.1 GB

Weights 17.1 GB KV cache @ 8K 0.75 GB Runtime overhead 0.6 GB Over budget 0.5 GB past 18.0 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	30.2 GB	31.5 GB	—	~8.0	−0.1% ppl	13.5 GB over
Q6_K	23.3 GB	24.6 GB	—	~10	−0.4% ppl	6.6 GB over
Q5_K_M	20.1 GB	21.5 GB	—	~12	−0.8% ppl	3.5 GB over
Q4_K_M	17.1 GB	18.5 GB	2K	~14	−1.9% ppl	0.5 GB over
Q3_K_M	13.9 GB	15.2 GB	37K	17	−5.4% ppl	Long context
Q2_K	11.9 GB	13.2 GB	58K	20	−15% ppl	Long context

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it.

How to run it

Ollama llama.cpp LM Studio MLX

terminal

$ pip install mlx-lm
$ mlx_lm.generate --model mlx-community/Qwen3-30B-A3B-4bit \
    --max-tokens 512 --prompt "Hello"

Apple's own array framework. The fastest path on Apple Silicon. More on MLX.

01Download is 17.1 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.

02macOS caps what the GPU may wire down at about 18.0 GB of 24 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.

03If it falls back to CPU silently, drop the context first, then step down a quantisation.

See all models for this rig Compare with another model