How fast is Qwen3 30B-A3B on an Mac?

Around 17 tokens per second. Token generation on Apple Silicon is limited by memory bandwidth, and this machine has 68 GB/s. Because this is a mixture-of-experts model only 3.3B of its 30.5B parameters are read per token, which is why it is faster than its size suggests.

How much memory does Qwen3 30B-A3B need?

17.4 GiB for the weights at Q4_K_M, plus 0.8 GiB for an 8K-token KV cache and about 1.7 GiB of runtime overhead — 19.8 GiB in total.

Home › Qwen3 30B-A3B › M1 16GB

Can an M1 16GB Mac run Qwen3 30B-A3B?

M1 · 16 GB unified memory · 68 GB/s · MacBook Air (M1), Mac mini (M1)

No — not at Q4_K_M.

Qwen3 30B-A3B needs about 19.8 GiB but an M1 16GB Mac has only ~13.0 GiB available for a model — you are 6.8 GiB short. macOS will swap to SSD and generation will crawl. There is a smaller quantisation that fits: see below.

Weights

17.4 GiB

30.5B params @ Q4_K_M

KV cache

0.8 GiB

8K context, FP16

Overhead

1.7 GiB

runtime + activations

Total needed

19.8 GiB

of ~13.0 GiB usable

Est. speed

17 tok/s

68 GB/s bandwidth

Max context

n/a

at Q4_K_M

Where the memory goes

Three things occupy memory when a model is loaded: the weights themselves, the KV cache that holds the conversation, and the runtime's own working buffers. Only the first is fixed — the KV cache grows with every token in your context.

Quantisation	Weights	Total	Tok/s	Fits?
FP16	56.8 GiB	61.2 GiB	5	No
Q8_0	30.2 GiB	33.2 GiB	10	No
Q6_K	23.4 GiB	26.2 GiB	12	No
Q5_K_M	20.2 GiB	22.8 GiB	14	No
Q4_K_M	17.4 GiB	19.8 GiB	17	No
Q3_K_M	13.8 GiB	16.1 GiB	21	No
Q2_K	10.7 GiB	12.7 GiB	27	Yes, but tight

The default. Best quality-per-gigabyte for most people.

How long a context fits

The KV cache is often what breaks a setup that looked fine at load time. Quantising it to 8-bit roughly halves its footprint with little measurable quality cost.

Context	KV cache	Total	FP16 KV	Q8 KV
2K	0.2 GiB	19.0 GiB	No	No
4K	0.4 GiB	19.3 GiB	No	No
8K	0.8 GiB	19.8 GiB	No	No
16K	1.5 GiB	20.9 GiB	No	No
32K	3.0 GiB	23.0 GiB	No	No
128K	12.0 GiB	35.6 GiB	No	No

What to run instead on an M1 16GB Mac

These are the largest models that fit comfortably on this machine at Q4_K_M with an 8K context.

Model	Size	Total	Tok/s
Qwen3 14B	14.8B	10.9 GiB	6	Yes, comfortably
Gemma 2 9B	9.24B	9.0 GiB	10	Yes, comfortably
Qwen3 8B	8.2B	6.8 GiB	11	Yes, comfortably
Llama 3.1 8B	8.03B	6.6 GiB	11	Yes, comfortably
DeepSeek-R1-Distill-Qwen-7B	7.62B	5.8 GiB	12	Yes, comfortably
Qwen2.5 7B	7.62B	5.8 GiB	12	Yes, comfortably

Macs that run Qwen3 30B-A3B comfortably

The smallest configuration that handles it is the M1 Max 32GB (MacBook Pro 14" (M1 Max)).

Mac	Memory	Bandwidth	Tok/s
M1 Max 32GB	32 GB	400 GB/s	99
M2 Max 32GB	32 GB	400 GB/s	99
M4 32GB	32 GB	120 GB/s	30
M3 Max 36GB	36 GB	300 GB/s	74
M4 Max 36GB	36 GB	410 GB/s	101
M4 Pro 48GB	48 GB	273 GB/s	68
M4 Max 48GB	48 GB	546 GB/s	135
M1 Max 64GB	64 GB	400 GB/s	99
M2 Ultra 64GB	64 GB	800 GB/s	198
M4 Pro 64GB	64 GB	273 GB/s	68
M4 Max 64GB	64 GB	546 GB/s	135
M2 Max 96GB	96 GB	400 GB/s	99

Common questions

Can an M1 16GB Mac run Qwen3 30B-A3B?: No. At Q4_K_M it needs about 19.8 GiB, and an M1 16GB Mac has roughly 13.0 GiB available for a model after macOS takes its share.
How fast is Qwen3 30B-A3B on an Mac?: Around 17 tokens per second. Token generation on Apple Silicon is limited by memory bandwidth, and this machine has 68 GB/s. Because this is a mixture-of-experts model only 3.3B of its 30.5B parameters are read per token, which is why it is faster than its size suggests.
How much memory does Qwen3 30B-A3B need?: 17.4 GiB for the weights at Q4_K_M, plus 0.8 GiB for an 8K-token KV cache and about 1.7 GiB of runtime overhead — 19.8 GiB in total.