With 16 GB unified memory (about 10.7 GB usable by the GPU), these are the best open models that fit. The top pick is DeepSeek Coder V2 Lite 16B (MoE) at Q4_0 (~9.9 GB, ~20 tok/s): ollama run deepseek-coder-v2:16b.
Best for coding: DeepSeek Coder V2 Lite 16B (MoE) (deepseek-coder-v2:16b), Qwen 2.5 Coder 14B (qwen2.5-coder:14b), Qwen 2.5 Coder 1.5B (qwen2.5-coder:1.5b-instruct-q8_0).
Runtimes available for this hardware: Ollama, LM Studio, llama.cpp, MLX.
Open the interactive checker for M1 16GB| # | Model | Quant | Memory needed | Fit | Speed | Command |
|---|---|---|---|---|---|---|
| 1 | DeepSeek Coder V2 Lite 16B (MoE) | Q4_0 | 9.9 GB | fits in fast memory | ~20 tok/s | ollama run deepseek-coder-v2:16b |
| 2 | Mistral Nemo 12B | Q5_K_M | 9.9 GB | fits in fast memory | ~6 tok/s | ollama run mistral-nemo:12b-instruct-2407-q5_K_M |
| 3 | DeepSeek R1 Distill Qwen 14B | Q4_K_M | 10.3 GB | fits in fast memory | ~6 tok/s | ollama run deepseek-r1:14b |
| 4 | Phi-4 14B | Q4_K_M | 10.4 GB | fits in fast memory | ~6 tok/s | ollama run phi4:14b |
| 5 | Qwen3 14B | Q4_K_M | 10.6 GB | fits in fast memory | ~6 tok/s | ollama run qwen3:14b |
| 6 | Gemma 3 12B | Q4_K_M | 9.4 GB | fits in fast memory | ~7 tok/s | ollama run gemma3:12b |
| 7 | Phi-4 Mini 3.8B | Q8_0 | 4.9 GB | fits in fast memory | ~13 tok/s | ollama run phi4-mini:3.8b-q8_0 |
| 8 | Qwen3 4B | Q8_0 | 5.2 GB | fits in fast memory | ~12 tok/s | ollama run qwen3:4b-q8_0 |
| 9 | Llama 3.2 Vision 11B | Q4_K_M | 8.9 GB | fits in fast memory | ~7 tok/s | ollama run llama3.2-vision:11b |
| 10 | Llama 3.2 3B | Q8_0 | 4.2 GB | fits in fast memory | ~16 tok/s | ollama run llama3.2:3b-instruct-q8_0 |
| 11 | Gemma 3 4B | Q8_0 | 5.8 GB | fits in fast memory | ~11 tok/s | ollama run gemma3:4b-it-q8_0 |
| 12 | tev1 4B (Together AI, decision) | Q8_0 | 5.4 GB | fits in fast memory | ~12 tok/s | ollama run tev1:4b-q8_0 |
Estimates, not benchmarks. Model sizes are ollama.com download sizes; memory needed adds headroom for ~8k tokens of context; speeds are rough figures from memory bandwidth. Data updated 2026-10-14.
A project by OnDevice Labs · llms.txt