By memory size

Local LLMs for a Mac
with 16GB of memory

On a Mac with 16GB of memory, models up to 8GB run comfortably alongside other apps: 15 of the 33 models measured here. The smartest is Qwen3.5-9B (84% on knowledge, 98% on math, 6.5GB). "Measured" here also counts the models measured for the series page, beyond the top page's text lineup.

Other sizes: 8GB · 16GB · 24GB · 32GB · 36GB · 48GB or more

To find your Mac's memory, choose the Apple menu → About This Mac (for example, 16 GB).

Picks by use

UseModelRule
If unsure, start hereOrnith-1.0-9BThe smartest that replies within 5 seconds (1 more within the margin)
Smartest (if you can wait)Qwen3.5-9BThe highest share of right answers (2 more within the margin)
Replies right awayGLM-4-9B-0414The smartest that replies within 1 second
English → Japanese translationNVIDIA-Nemotron-3.5-Bolt-E4B-BF16The highest translation score (4 more within the margin)

Runs comfortably (up to 8GB)

ModelMemoryReply timeKnowledgeMathEN→JA
Qwen3.5-9BAlibaba6.5GBabout 40.3 s84%98%—
Ornith-1.0-9Bornith-ai6.2GBabout 3.8 s85%94%—
Qwen3.5-4BAlibaba3.5GBabout 29.7 s81%96%—
Ornith-1.5-9Bornith-ai6.4GBabout 2.5 s77%94%33 pts
gemma-4-E4B-itGoogle5.4GBabout 2.6 s79%92%32 pts
NVIDIA-Nemotron-3.5-Bolt-E4B-BF16NVIDIA6.5GBabout 2.6 s76%93%34 pts
Qwen3-4BAlibaba3.9GBabout 3.1 s72%93%29 pts
MiniCPM5-2BOpenBMB2GBabout 1.5 s73%90%23 pts
DeepSeek-R1-0528-Qwen3-8BDeepSeek6.4GBabout 9.4 s72%89%23 pts
LFM2.5-2.6BLiquid AI2GBabout 2.3 s73%79%29 pts
NVIDIA-Nemotron-3-Nano-4B-BF16NVIDIA3.3GBabout 1.9 s72%80%24 pts
LFM2.5-8B-A1BLiquid AI5.4GBabout 1.7 s71%78%29 pts
GLM-4-9B-0414Z.ai6.7GBabout 0.1 s72%77%32 pts
LFM2.5-1.2B-JP-202606Liquid AI1GBabout 0.2 s51%63%33 pts
DeepSeek-R1-Distill-Qwen-1.5BDeepSeek1.5GBabout 1.7 s23%21%3 pts

Runs with heavy apps closed

More than half the memory, but up to 10.4GB should run. Close heavy apps other than a browser first.

ModelMemoryReply timeKnowledgeMathEN→JA
gemma-4-12B-itGoogle8.1GBabout 7.5 s85%97%35 pts
NVIDIA-Nemotron-Nano-12B-v2NVIDIA8.1GBabout 6.8 s80%94%31 pts

Measured on a Mac with this memory

Numbers measured on the Mac mini (16GB) itself; the reply times are from that Mac too.

ModelGeneration speedMemory usedReply timeKnowledgeMath
MiniCPM5-2BOpenBMB81.6 tok/s2.1GBabout 2.9 s70%90%
qwen3.5:4b44.2 tok/s3.4GBabout 63.6 sNot measuredNot measured
qwen3.5:9b33.4 tok/s7.7GBabout 47.8 sNot measuredNot measured
gemma4:12b16.3 tok/s8.1GBabout 26.3 sNot measuredNot measured

Apple list price, tax included (guide)

The tax-included list price is unconfirmed. The buy-page terms forbid automated fetching, so this site did not retrieve yen amounts.

MemoryApple list price, tax included (guide)Difference from the size below
8GBUnconfirmed—
16GBUnconfirmedUnconfirmed
24GBUnconfirmedUnconfirmed
32GBUnconfirmedUnconfirmed
36GBUnconfirmedUnconfirmed
48GB or moreUnconfirmedUnconfirmed

Source: Apple’s official buy pages (www.apple.com/jp/shop/buy-mac/mac-mini / www.apple.com/jp/shop/buy-mac/mac-studio). Checked 2026-10-24. No outbound link.

About this guide

  • Memory was measured on a Mac Studio (M5 Max, 36GB). Memory use is about the same on any Apple silicon Mac, so it carries over.
  • Reply times are from this Mac. Slower chips (a MacBook Air, say) reply more slowly.
  • "Comfortable" means the model takes at most half the memory; "with heavy apps closed" up to 65%. The picks follow the same rules as the text page, among the models that fit.
  • What "9B", "A3B" or "it" in the names mean: how to read a model name.

Task recommendations and capabilities · Measurements by model