Can It Run?
HomeQwen3 30B-A3B › M1 8GB

Can an M1 8GB Mac run Qwen3 30B-A3B?

M1 · 8 GB unified memory · 68 GB/s · MacBook Air (M1), MacBook Pro 13" (M1)

No — not at Q4_K_M.

Qwen3 30B-A3B needs about 19.8 GiB but an M1 8GB Mac has only ~5.0 GiB available for a model — you are 14.8 GiB short. macOS will swap to SSD and generation will crawl.

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 ~5.0 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.

QuantisationWeightsTotalTok/sFits?
FP1656.8 GiB61.2 GiB5No
Q8_030.2 GiB33.2 GiB10No
Q6_K23.4 GiB26.2 GiB12No
Q5_K_M20.2 GiB22.8 GiB14No
Q4_K_M17.4 GiB19.8 GiB17No
Q3_K_M13.8 GiB16.1 GiB21No
Q2_K10.7 GiB12.7 GiB27No

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.

ContextKV cacheTotalFP16 KVQ8 KV
2K0.2 GiB19.0 GiBNoNo
4K0.4 GiB19.3 GiBNoNo
8K0.8 GiB19.8 GiBNoNo
16K1.5 GiB20.9 GiBNoNo
32K3.0 GiB23.0 GiBNoNo
128K12.0 GiB35.6 GiBNoNo

What to run instead on an M1 8GB Mac

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

ModelSizeTotalTok/s
Llama 3.2 3B3.21B3.6 GiB28Yes, comfortably
Qwen2.5 3B3.09B2.9 GiB29Yes, comfortably
Gemma 2 2B2.61B3.0 GiB34Yes, comfortably
Qwen2.5 1.5B1.54B1.9 GiB58Yes, comfortably
Llama 3.2 1B1.24B1.8 GiB72Yes, comfortably

Macs that run Qwen3 30B-A3B comfortably

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

MacMemoryBandwidthTok/s
M1 Max 32GB32 GB400 GB/s99
M2 Max 32GB32 GB400 GB/s99
M4 32GB32 GB120 GB/s30
M3 Max 36GB36 GB300 GB/s74
M4 Max 36GB36 GB410 GB/s101
M4 Pro 48GB48 GB273 GB/s68
M4 Max 48GB48 GB546 GB/s135
M1 Max 64GB64 GB400 GB/s99
M2 Ultra 64GB64 GB800 GB/s198
M4 Pro 64GB64 GB273 GB/s68
M4 Max 64GB64 GB546 GB/s135
M2 Max 96GB96 GB400 GB/s99

Common questions

Can an M1 8GB Mac run Qwen3 30B-A3B?
No. At Q4_K_M it needs about 19.8 GiB, and an M1 8GB Mac has roughly 5.0 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.