Yes — with 125.5 GB to spare

Qwen3 30B-A3B at Q4_K_M fits your M2 Ultra · 192 GB entirely in unified memory at 8K context, at an estimated 112 tokens per second. There is room for its full 128K window.

Fully in unified memory 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? →

The VRAM budget

weights 17.1 GB

Weights 17.1 GB KV cache @ 8K 0.75 GB Runtime overhead 0.6 GB Free 125.5 GB of 144.0 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	30.2 GB	31.5 GB	128K	64	−0.1% ppl	Long context
Q6_K	23.3 GB	24.6 GB	128K	83	−0.4% ppl	Long context
Q5_K_M	20.1 GB	21.5 GB	128K	96	−0.8% ppl	Long context
Q4_K_M	17.1 GB	18.5 GB	128K	112	−1.9% ppl	Recommended
Q3_K_M	13.9 GB	15.2 GB	128K	139	−5.4% ppl	Long context
Q2_K	11.9 GB	13.2 GB	128K	162	−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 144.0 GB of 192 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.

03There is room to go to the model's full 128K context on this card.

See all models for this rig Compare with another model