Yes — with 17.5 GB to spare

Qwen3 Coder 30B-A3B at Q4_K_M fits your M4 Pro · 48 GB entirely in unified memory at 8K context, at an estimated 38 tokens per second. Past 194K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.

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 17.5 GB of 36.0 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	30.2 GB	31.5 GB	55K	22	−0.1% ppl	Long context
Q6_K	23.3 GB	24.6 GB	129K	28	−0.4% ppl	Long context
Q5_K_M	20.1 GB	21.5 GB	162K	33	−0.8% ppl	Long context
Q4_K_M	17.1 GB	18.5 GB	194K	38	−1.9% ppl	Recommended
Q3_K_M	13.9 GB	15.2 GB	229K	47	−5.4% ppl	Long context
Q2_K	11.9 GB	13.2 GB	250K	55	−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 36.0 GB of 48 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.

03There is room to go to 194K context on this card.

See all models for this rig Compare with another model