How fast is Mixtral 8x7B on an Mac?

Around 6 tokens per second. Token generation on Apple Silicon is limited by memory bandwidth, and this machine has 100 GB/s. Because this is a mixture-of-experts model only 12.9B of its 46.7B parameters are read per token, which is why it is faster than its size suggests.

How much memory does Mixtral 8x7B need?

26.6 GiB for the weights at Q4_K_M, plus 1.0 GiB for an 8K-token KV cache and about 2.1 GiB of runtime overhead — 29.8 GiB in total.

Home › Mixtral 8x7B › M2 16GB

Can an M2 16GB Mac run Mixtral 8x7B?

M2 · 16 GB unified memory · 100 GB/s · MacBook Air 13" (M2), MacBook Air 15" (M2)

No — not at Q4_K_M.

Mixtral 8x7B needs about 29.8 GiB but an M2 16GB Mac has only ~13.0 GiB available for a model — you are 16.8 GiB short. macOS will swap to SSD and generation will crawl.

Weights

26.6 GiB

46.7B params @ Q4_K_M

KV cache

1.0 GiB

8K context, FP16

Overhead

2.1 GiB

runtime + activations

Total needed

29.8 GiB

of ~13.0 GiB usable

Est. speed

6 tok/s

100 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	87.0 GiB	93.1 GiB	2	No
Q8_0	46.2 GiB	50.3 GiB	4	No
Q6_K	35.9 GiB	39.5 GiB	5	No
Q5_K_M	31.0 GiB	34.3 GiB	5	No
Q4_K_M	26.6 GiB	29.8 GiB	6	No
Q3_K_M	21.2 GiB	24.1 GiB	8	No
Q2_K	16.3 GiB	18.9 GiB	10	No

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	0.3 GiB	28.8 GiB	No	No
4K	0.5 GiB	29.1 GiB	No	No
8K	1.0 GiB	29.8 GiB	No	No
16K	2.0 GiB	31.1 GiB	No	No
32K	4.0 GiB	33.7 GiB	No	No

What to run instead on an M2 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	9	Yes, comfortably
Gemma 2 9B	9.24B	9.0 GiB	14	Yes, comfortably
Qwen3 8B	8.2B	6.8 GiB	16	Yes, comfortably
Llama 3.1 8B	8.03B	6.6 GiB	16	Yes, comfortably
DeepSeek-R1-Distill-Qwen-7B	7.62B	5.8 GiB	17	Yes, comfortably
Qwen2.5 7B	7.62B	5.8 GiB	17	Yes, comfortably

Macs that run Mixtral 8x7B comfortably

The smallest configuration that handles it is the M4 Pro 48GB (Mac mini (M4 Pro)).

Mac	Memory	Bandwidth	Tok/s
M4 Pro 48GB	48 GB	273 GB/s	17
M4 Max 48GB	48 GB	546 GB/s	35
M1 Max 64GB	64 GB	400 GB/s	25
M2 Ultra 64GB	64 GB	800 GB/s	51
M4 Pro 64GB	64 GB	273 GB/s	17
M4 Max 64GB	64 GB	546 GB/s	35
M2 Max 96GB	96 GB	400 GB/s	25
M3 Ultra 96GB	96 GB	819 GB/s	52
M3 Max 128GB	128 GB	400 GB/s	25
M4 Max 128GB	128 GB	546 GB/s	35
M2 Ultra 192GB	192 GB	800 GB/s	51
M3 Ultra 256GB	256 GB	819 GB/s	52

Common questions

Can an M2 16GB Mac run Mixtral 8x7B?: No. At Q4_K_M it needs about 29.8 GiB, and an M2 16GB Mac has roughly 13.0 GiB available for a model after macOS takes its share.
How fast is Mixtral 8x7B on an Mac?: Around 6 tokens per second. Token generation on Apple Silicon is limited by memory bandwidth, and this machine has 100 GB/s. Because this is a mixture-of-experts model only 12.9B of its 46.7B parameters are read per token, which is why it is faster than its size suggests.
How much memory does Mixtral 8x7B need?: 26.6 GiB for the weights at Q4_K_M, plus 1.0 GiB for an 8K-token KV cache and about 2.1 GiB of runtime overhead — 29.8 GiB in total.