Model Tested Follow
What can I run · updated Oct 11, 2026

Local LLMs that run on a Mac with 16 GB of memory

16 of the 56 models we've tested fit, with room for a normal-length chat. The best one is Granite 4.2 8B, scoring 77 out of 100.

Mac 16 GB Mac 24 GB Mac 32 GB Mac 48 GB Mac 64 GB Mac 96 GB Mac 128 GB
#ModelScoreCodingDocumentsDownloadMemory
1 Granite 4.2 8B 77 77 78 Q6 9.2 GB
2 Qwen3.5-9B 72 47 97 Q6 9.6 GB
3 Ministral 3 14B 2512 44 43 45 Q4 10.4 GB
4 Qwen3 VL 8B Instruct 39 37 41 Q6 9 GB
5 Ministral 3 8B 2512 37 30 43 Q6 9.1 GB
6 Gemma 3 12B
ollama run gemma3:12b
 35 30 40 Q5 10.3 GB
7 Qwen2.5 7B Instruct
ollama run qwen2.5:7b
 24 10 37 Q8 9.2 GB
8 Llama 3.3 8B Instruct (Q4, Mac)
ollama run hf.co/bartowski/allura-forge_Llama-3.3-8B-Instruct-GGUF:Q4_K_M
 23 13 33 Q4 6 GB
9 Mistral Nemo
ollama run mistral-nemo
 23 10 36 Q4 9.4 GB
10 Granite 4.0 Micro (Q4, Mac)
ollama run granite4:micro-h
 22 13 31 Q4 3.2 GB
11 Ministral 3 3B 2512 21 10 32 Q8 5.6 GB
12 Llama 3.1 8B Instruct
ollama run llama3.1:8b
 15 3 26 Q8 9.6 GB
13 Gemma 3 4B
ollama run gemma3:4b
 14 3 25 Q8 5.7 GB
14 Reka Edge 8 0 16 Q8 9.2 GB
15 Llama 3.2 3B Instruct
ollama run llama3.2:3b
 6 0 13 Q8 4.5 GB
16 Llama 3.2 1B Instruct (Q4, Mac)
ollama run llama3.2:1b-instruct-q4_K_M
 5 0 9 Q4 1.9 GB

"Download" is the biggest version that fits on Mac with 16 GB; "Memory" is roughly what that version needs. Smaller versions also work and leave more room. Q4 or Q8?

Top models that don't fit

  • Qwen3.6 27B (97/100) needs about 19.6 GB even in its smallest version.
  • gpt-oss-120b (96/100) needs about 63.3 GB even in its smallest version.
  • Muse Glimmer 30B (94/100) needs about 19.1 GB even in its smallest version.
  • Ling 3.0 Flash (94/100) needs about 83.5 GB even in its smallest version.
  • GLM 4.5V (93/100) needs about 67.4 GB even in its smallest version.

Not sure how much memory you have? Here's how to check.