Yes — with 77.5 GB to spare

Qwen3 Coder 30B-A3B at Q4_K_M fits your M4 Max · 128 GB entirely in unified memory at 8K context, at an estimated 77 tokens per second. There is room for its full 256K window.

Fully in unified memory 8K context Q4_K_M · 17.1 GB Apache 2.0 Released Jul 2025

Agentic coding MoE with a 256K native window. Still the most-downloaded local code model.

What hardware do I need for Qwen3 Coder 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 77.5 GB of 96.0 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	30.2 GB	31.5 GB	256K	44	−0.1% ppl	Long context
Q6_K	23.3 GB	24.6 GB	256K	56	−0.4% ppl	Long context
Q5_K_M	20.1 GB	21.5 GB	256K	65	−0.8% ppl	Long context
Q4_K_M	17.1 GB	18.5 GB	256K	77	−1.9% ppl	Recommended
Q3_K_M	13.9 GB	15.2 GB	256K	95	−5.4% ppl	Long context
Q2_K	11.9 GB	13.2 GB	256K	111	−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-Coder-30B-A3B-Instruct-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 96.0 GB of 128 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.

03There is room to go to the model's full 256K context on this card.

See all models for this rig Compare with another model