Outlier · Local AI for Mac

Can a Mac run Qwen3 14B?

Quick answer

Yes. Qwen3 14B needs about 24 GB for short chats and 32 GB for long 32,000-token work, by our cautious rule, not measured by us.

On the MacBook Pro M3 Pro, expect about 3.6 to 7.2 tokens/s, estimated. On the Mac Studio M1 Ultra, expect about 19 to 39 tokens/s, estimated.

Size and tasks

Set aside 8.31 GB of free disk space. This 14B dense model can chat. If you compare total parameters across our list, you will find 13 smaller models and 18 larger models. Dense means the whole model is used for each token.

This Qwen chat model and the nearby Phi download share a total parameter count and memory requirement. Their files differ in size, so storage is a direct comparison you can make while keeping the same memory budget. A nearby Gemma adds image reading and needs more memory. Think about whether you want to work with pictures before making that jump. At this Qwen model's minimum there is little memory to spare. Larger configurations leave more room, and the chip rates remain estimates for all the Macs shown.

The exact model ID is Qwen3-14B.

How we work this out

Weights take 8.31 GB. L = 40 attention layers, kv_heads = 8, head_dim = 128. We count every attention layer in full and keep all expert weights in memory.

KV GB = 2 × L × kv_heads × head_dim × 2 bytes × tokens ÷ 1,000,000,000. The cache is 16-bit.

Need = weights + rounded KV + runtime, rounded to two decimals. Runtime and activations take 2 GB. GPU limits below are rounded to eight decimals.

CalculationShort chatsLong work
Tokens8,19232,768
KV sum in GB1.342177285.36870912
KV rounded to two decimals in GB1.345.37
Need in GB11.6515.68
First memory size in GB1824
Usable GPU memory in GB, rounded1216
Close threshold in GB, rounded11.415.2
Close margin stepNext memory sizeNext memory size
Minimum Mac memory in GB2432
Usable GPU memory is 2/3 of Mac memory up to 36 GB and 3/4 above that. Pick the first size that holds the need from 8, 16, 18, 24, 32, 36, 48, 64, 96, 128, 192, 256, 512 GB. If need is above 95% of usable memory, within 5%, take the next memory size.

Which Macs can run it

The memory checks, comparisons and upgrade advice below use our long 32,000-token work figure. Use the short-chat figure above for shorter conversations.

Your chip name alone cannot settle the fit. Match the memory in your Mac to the options below. Across 38 Mac models, 27 offer enough memory in at least one configuration. That leaves 11 Macs needing a larger capacity than their listed options offer. Read tight as fitting with little memory to spare.

There are no measured speeds for this model in our snapshot. Both the chip rates and the memory minimum use rules. Read the source beside a range when comparing it with a model we have tested.

Macs grouped by their smallest fitting memory option
Mac and chipEvery listed memory optionChip speed source
First fitting configuration 32 GB
MacBook Pro M1 Pro Apple M1 Pro 16 GB does not fit. Next 32 GB configuration.
32 GB tight.
about 4.8 to 9.6 tokens/s estimate, not measured by us
How we estimate speed 4.81 to 9.63 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 200 GB/s divided by active weights in GB
MacBook Pro M1 Max Apple M1 Max 32 GB tight.
64 GB fits.
about 9.6 to 19 tokens/s estimate, not measured by us
How we estimate speed 9.62 to 19.26 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 400 GB/s divided by active weights in GB
MacBook Pro M2 Pro Apple M2 Pro 16 GB does not fit. Next 32 GB configuration.
32 GB tight.
about 4.8 to 9.6 tokens/s estimate, not measured by us
How we estimate speed 4.81 to 9.63 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 200 GB/s divided by active weights in GB
MacBook Pro M2 Max Apple M2 Max 32 GB tight.
64 GB fits.
96 GB fits.
about 9.6 to 19 tokens/s estimate, not measured by us
How we estimate speed 9.62 to 19.26 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 400 GB/s divided by active weights in GB
MacBook Pro 14 M4 Apple M4 16 GB does not fit. Next 32 GB configuration.
24 GB does not fit. Next 32 GB configuration.
32 GB tight.
about 2.9 to 5.8 tokens/s estimate, not measured by us
How we estimate speed 2.88 to 5.78 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 120 GB/s divided by active weights in GB
iMac M4 Apple M4 16 GB does not fit. Next 32 GB configuration.
24 GB does not fit. Next 32 GB configuration.
32 GB tight.
about 2.9 to 5.8 tokens/s estimate, not measured by us
How we estimate speed 2.88 to 5.78 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 120 GB/s divided by active weights in GB
Mac mini M4 Apple M4 16 GB does not fit. Next 32 GB configuration.
24 GB does not fit. Next 32 GB configuration.
32 GB tight.
about 2.9 to 5.8 tokens/s estimate, not measured by us
How we estimate speed 2.88 to 5.78 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 120 GB/s divided by active weights in GB
MacBook Air 13 M4 Apple M4 16 GB does not fit. Next 32 GB configuration.
24 GB does not fit. Next 32 GB configuration.
32 GB tight.
about 2.9 to 5.8 tokens/s estimate, not measured by us
How we estimate speed 2.88 to 5.78 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 120 GB/s divided by active weights in GB
MacBook Air 15 M4 Apple M4 16 GB does not fit. Next 32 GB configuration.
24 GB does not fit. Next 32 GB configuration.
32 GB tight.
about 2.9 to 5.8 tokens/s estimate, not measured by us
How we estimate speed 2.88 to 5.78 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 120 GB/s divided by active weights in GB
MacBook Air 13 M5 Apple M5 16 GB does not fit. Next 32 GB configuration.
24 GB does not fit. Next 32 GB configuration.
32 GB tight.
about 3.7 to 7.4 tokens/s estimate, not measured by us
How we estimate speed 3.68 to 7.37 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 153 GB/s divided by active weights in GB
MacBook Air 15 M5 Apple M5 16 GB does not fit. Next 32 GB configuration.
24 GB does not fit. Next 32 GB configuration.
32 GB tight.
about 3.7 to 7.4 tokens/s estimate, not measured by us
How we estimate speed 3.68 to 7.37 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 153 GB/s divided by active weights in GB
MacBook Pro 14 M6 Apple M6 16 GB does not fit. Next 32 GB configuration.
24 GB does not fit. Next 32 GB configuration.
32 GB tight.
about 3.7 to 8.2 tokens/s estimate, not measured by us
How we estimate speed 3.68 to 8.19 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 153-170 GB/s divided by active weights in GB
Mac mini M6 Apple M6 16 GB does not fit. Next 32 GB configuration.
24 GB does not fit. Next 32 GB configuration.
32 GB tight.
about 3.7 to 8.2 tokens/s estimate, not measured by us
How we estimate speed 3.68 to 8.19 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 153-170 GB/s divided by active weights in GB
iMac M6 Apple M6 16 GB does not fit. Next 32 GB configuration.
24 GB does not fit. Next 32 GB configuration.
32 GB tight.
about 3.7 to 8.2 tokens/s estimate, not measured by us
How we estimate speed 3.68 to 8.19 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 153-170 GB/s divided by active weights in GB
First fitting configuration 36 GB
MacBook Pro M3 Pro Apple M3 Pro 18 GB does not fit. Next 36 GB configuration.
36 GB fits.
about 3.6 to 7.2 tokens/s estimate, not measured by us
How we estimate speed 3.61 to 7.23 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 150 GB/s divided by active weights in GB
MacBook Pro M3 Max Apple M3 Max 36 GB fits.
48 GB fits.
64 GB fits.
96 GB fits.
128 GB fits.
about 7.2 to 19 tokens/s estimate, not measured by us
How we estimate speed 7.22 to 19.26 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 300-400 GB/s divided by active weights in GB
MacBook Pro M4 Max Apple M4 Max 36 GB fits.
48 GB fits.
64 GB fits.
128 GB fits.
about 9.9 to 26 tokens/s estimate, not measured by us
How we estimate speed 9.86 to 26.29 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 410-546 GB/s divided by active weights in GB
MacBook Pro M5 Max Apple M5 Max 36 GB fits.
48 GB fits.
64 GB fits.
128 GB fits.
about 11 to 30 tokens/s estimate, not measured by us
How we estimate speed 11.07 to 29.56 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 460-614 GB/s divided by active weights in GB
Mac Studio M5 Max Apple M5 Max 36 GB fits.
48 GB fits.
64 GB fits.
128 GB fits.
about 11 to 30 tokens/s estimate, not measured by us
How we estimate speed 11.07 to 29.56 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 460-614 GB/s divided by active weights in GB
First fitting configuration 48 GB
Mac mini M4 Pro Apple M4 Pro 24 GB does not fit. Next 48 GB configuration.
48 GB fits.
64 GB fits.
about 6.6 to 13 tokens/s estimate, not measured by us
How we estimate speed 6.57 to 13.15 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 273 GB/s divided by active weights in GB
MacBook Pro M4 Pro Apple M4 Pro 24 GB does not fit. Next 48 GB configuration.
48 GB fits.
about 6.6 to 13 tokens/s estimate, not measured by us
How we estimate speed 6.57 to 13.15 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 273 GB/s divided by active weights in GB
MacBook Pro M5 Pro Apple M5 Pro 24 GB does not fit. Next 48 GB configuration.
48 GB fits.
64 GB fits.
about 7.4 to 15 tokens/s estimate, not measured by us
How we estimate speed 7.38 to 14.78 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 307 GB/s divided by active weights in GB
Mac mini M5 Pro Apple M5 Pro 24 GB does not fit. Next 48 GB configuration.
48 GB fits.
64 GB fits.
about 7.4 to 15 tokens/s estimate, not measured by us
How we estimate speed 7.38 to 14.78 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 307 GB/s divided by active weights in GB
First fitting configuration 64 GB
Mac Studio M1 Ultra Apple M1 Ultra 64 GB fits.
128 GB fits.
about 19 to 39 tokens/s estimate, not measured by us
How we estimate speed 19.25 to 38.51 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 800 GB/s divided by active weights in GB
Mac Studio M2 Ultra Apple M2 Ultra 64 GB fits.
128 GB fits.
192 GB fits.
about 19 to 39 tokens/s estimate, not measured by us
How we estimate speed 19.25 to 38.51 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 800 GB/s divided by active weights in GB
First fitting configuration 96 GB
Mac Studio M3 Ultra Apple M3 Ultra 96 GB fits.
256 GB fits.
512 GB fits.
about 20 to 39 tokens/s estimate, not measured by us
How we estimate speed 19.71 to 39.43 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 819 GB/s divided by active weights in GB
Mac Studio M5 Ultra Apple M5 Ultra 96 GB fits.
256 GB fits.
512 GB fits.
about 29 to 58 tokens/s estimate, not measured by us
How we estimate speed 28.88 to 57.77 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 1200 GB/s divided by active weights in GB
No fitting configuration listed
MacBook Air M1 Apple M1 8 GB does not fit. Next 32 GB on a different listed Mac.
16 GB does not fit. Next 32 GB on a different listed Mac.
about 1.6 to 3.3 tokens/s estimate, not measured by us
How we estimate speed 1.64 to 3.29 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 68.25 GB/s divided by active weights in GB
MacBook Pro 13 M1 Apple M1 8 GB does not fit. Next 32 GB on a different listed Mac.
16 GB does not fit. Next 32 GB on a different listed Mac.
about 1.6 to 3.3 tokens/s estimate, not measured by us
How we estimate speed 1.64 to 3.29 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 68.25 GB/s divided by active weights in GB
Mac mini M1 Apple M1 8 GB does not fit. Next 32 GB on a different listed Mac.
16 GB does not fit. Next 32 GB on a different listed Mac.
about 1.6 to 3.3 tokens/s estimate, not measured by us
How we estimate speed 1.64 to 3.29 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 68.25 GB/s divided by active weights in GB
iMac M1 Apple M1 8 GB does not fit. Next 32 GB on a different listed Mac.
16 GB does not fit. Next 32 GB on a different listed Mac.
about 1.6 to 3.3 tokens/s estimate, not measured by us
How we estimate speed 1.64 to 3.29 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 68.25 GB/s divided by active weights in GB
MacBook Air M2 Apple M2 8 GB does not fit. Next 32 GB on a different listed Mac.
16 GB does not fit. Next 32 GB on a different listed Mac.
24 GB does not fit. Next 32 GB on a different listed Mac.
about 2.4 to 4.8 tokens/s estimate, not measured by us
How we estimate speed 2.4 to 4.82 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 100 GB/s divided by active weights in GB
MacBook Pro 13 M2 Apple M2 8 GB does not fit. Next 32 GB on a different listed Mac.
16 GB does not fit. Next 32 GB on a different listed Mac.
24 GB does not fit. Next 32 GB on a different listed Mac.
about 2.4 to 4.8 tokens/s estimate, not measured by us
How we estimate speed 2.4 to 4.82 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 100 GB/s divided by active weights in GB
Mac mini M2 Apple M2 8 GB does not fit. Next 32 GB on a different listed Mac.
16 GB does not fit. Next 32 GB on a different listed Mac.
24 GB does not fit. Next 32 GB on a different listed Mac.
about 2.4 to 4.8 tokens/s estimate, not measured by us
How we estimate speed 2.4 to 4.82 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 100 GB/s divided by active weights in GB
MacBook Air 13 M3 Apple M3 8 GB does not fit. Next 32 GB on a different listed Mac.
16 GB does not fit. Next 32 GB on a different listed Mac.
24 GB does not fit. Next 32 GB on a different listed Mac.
about 2.4 to 4.8 tokens/s estimate, not measured by us
How we estimate speed 2.4 to 4.82 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 100 GB/s divided by active weights in GB
MacBook Air 15 M3 Apple M3 8 GB does not fit. Next 32 GB on a different listed Mac.
16 GB does not fit. Next 32 GB on a different listed Mac.
24 GB does not fit. Next 32 GB on a different listed Mac.
about 2.4 to 4.8 tokens/s estimate, not measured by us
How we estimate speed 2.4 to 4.82 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 100 GB/s divided by active weights in GB
iMac M3 Apple M3 8 GB does not fit. Next 32 GB on a different listed Mac.
16 GB does not fit. Next 32 GB on a different listed Mac.
24 GB does not fit. Next 32 GB on a different listed Mac.
about 2.4 to 4.8 tokens/s estimate, not measured by us
How we estimate speed 2.4 to 4.82 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 100 GB/s divided by active weights in GB
MacBook Neo Apple A18 Pro 8 GB does not fit. Next 32 GB on a different listed Mac. about 1.4 to 2.9 tokens/s estimate, not measured by us
How we estimate speed 1.44 to 2.89 tokens/s; estimate, not measured by us; 0.20 to 0.40 x Mac bandwidth 60 GB/s divided by active weights in GB

Nearby models by total parameter count

Compare these similar-sized downloads if you want a different memory requirement or set of capabilities.

To chat, you could try Phi 4. Its long-work minimum is the same 32 GB of memory. Its size is 14B dense. Its download uses 0.06 GB less disk space. It covers the same tasks.

Gemma 3 12B (QAT) can chat and read images. Its size is 12B dense. Its download uses 0.28 GB less disk space. Its long-work minimum is 48 GB of memory, 16 GB more.

You could use Qwen3.5 9B to chat. Its measured minimum is 12 GB of memory, 20 GB less. Its download uses 3.27 GB less disk space. Its size is 9B dense. It covers the same tasks.

See the 32 GB memory page to compare the other models you could run with that much memory.

Context and data dates

Memory minimums use a 32K context; longer contexts need more memory. This model starts with a 32768-token context. That is the text it can keep in view as you talk. When planning longer conversations, leave more memory available than the minimum shown here.

The model source date is 2026-11-08. Figures as of 8 November 2026.

Mac source.

Apple technical specifications (apple.com/mac and the specs page of each Mac, read 2026-11-07; the iMac M6 page says only "up to 170GB/s", so its low end, 153 GB/s, is the 16 GB figure for the same M6 chip on the Mac mini page); table last changed 2026-11-07

Chip ratio source.

llama.cpp's public Apple-silicon benchmark (github.com/ggml-org/llama.cpp/discussions/4167, read 2026-11-07): LLaMA 7B Q4_0 text generation, as a ratio to the M1 Ultra 48-core GPU

Model date source.

Dates come from each source text; otherwise table last changed 2026-10-19

Outlier Pro: $39 once

Download free Buy Pro

Free to start (Nano and Lite). macOS 15+, Apple silicon. Refund window: 30 days, no questions asked. Priced in US dollars. Checkout shows your currency and any local tax.

Try Outlier on your Mac

Choose a Mac configuration with enough memory for Qwen3 14B, then download Outlier to get started.

Download Outlier