Skip to content

iMac M1 16GB

Apple · M1 · 16GB Unified Memory · Can run 61 models

Buy Apple
Manufacturer Apple
Unified Mem 16 GB
Chip M1
CPU Cores 8
GPU Cores 8
Neural Engine 16
Bandwidth 68 GB/s
MSRP $1,499
Released Apr 20, 2021

AI Notes

The iMac M1 16GB is an all-in-one desktop that doubles as a local AI workstation. With 16GB unified memory and 68 GB/s bandwidth, it handles 7B models well and can run 13B models with quantization. Its active cooling system helps maintain consistent performance during long inference sessions.

Compatible Models

Model Parameters Best Quant VRAM Used Fit Est. Speed
Qwen 3 0.6B 600M Q4_K_M 2.5 GB Runs ~27 tok/s
Qwen 3.5 0.8B 800M Q4_K_M 1.5 GB Runs ~45 tok/s
Gemma 3 1B 1B Q8_0 2 GB Runs ~34 tok/s
Llama 3.2 1B 1B Q8_0 3 GB Runs ~23 tok/s
DeepSeek R1 1.5B 1.5B Q8_0 3 GB Runs ~23 tok/s
Gemma 2 2B 2B Q8_0 4 GB Runs ~17 tok/s
Gemma 3n E2B 2B Q4_K_M 3.3 GB Runs ~21 tok/s
Gemma 4 E2B 2B Q4_K_M 4 GB Runs ~17 tok/s
Qwen 3.5 2B 2B Q4_K_M 3 GB Runs ~23 tok/s
Llama 3.2 3B 3B Q8_0 5 GB Runs ~14 tok/s
Phi-3 Mini 3.8B 3.8B Q8_0 5.8 GB Runs ~12 tok/s
Phi-4 Mini 3.8B 3.8B Q4_K_M 4.5 GB Runs ~15 tok/s
Gemma 3 4B 4B Q4_K_M 5 GB Runs ~14 tok/s
Gemma 3n E4B 4B Q4_K_M 4.5 GB Runs ~15 tok/s
Gemma 4 E4B 4B Q4_K_M 6 GB Runs ~11 tok/s
Qwen 3 4B 4B Q4_K_M 4.5 GB Runs ~15 tok/s
Qwen 3.5 4B 4B Q4_K_M 4.5 GB Runs ~15 tok/s
DeepSeek R1 7B 7B Q8_0 9 GB Runs ~8 tok/s
Falcon 3 7B 7B Q4_K_M 6.8 GB Runs ~10 tok/s
Mistral 7B 7B Q8_0 9 GB Runs ~8 tok/s
Qwen 2.5 7B 7B Q8_0 9 GB Runs ~8 tok/s
Qwen 2.5 Coder 7B 7B Q8_0 9 GB Runs ~8 tok/s
Qwen 2.5 VL 7B 7B Q4_K_M 7 GB Runs ~10 tok/s
Aya Expanse 8B 8B Q4_K_M 6.5 GB Runs ~10 tok/s
Cogito 8B 8B Q4_K_M 7.5 GB Runs ~9 tok/s
DeepSeek R1 8B 8B Q4_K_M 7.5 GB Runs ~9 tok/s
Llama 3.1 8B 8B Q8_0 10 GB Runs ~7 tok/s
Nemotron 3 Nano 8B 8B Q4_K_M 7.5 GB Runs ~9 tok/s
Qwen 3 8B 8B Q4_K_M 7.5 GB Runs ~9 tok/s
Gemma 2 9B 9B Q8_0 11 GB Runs ~6 tok/s
Qwen 3.5 9B 9B Q4_K_M 7.5 GB Runs ~9 tok/s
Falcon 3 10B 10B Q4_K_M 8.5 GB Runs ~8 tok/s
Llama 3.2 Vision 11B 11B Q4_K_M 8.5 GB Runs ~8 tok/s
Gemma 3 12B 12B Q4_K_M 10.5 GB Runs ~6 tok/s
Mistral Nemo 12B 12B Q4_K_M 9.5 GB Runs ~7 tok/s
DeepSeek R1 14B 14B Q4_K_M 9.9 GB Runs ~7 tok/s
Phi-4 14B 14B Q4_K_M 9.9 GB Runs ~7 tok/s
Phi-4 Reasoning 14B 14B Q4_K_M 11 GB Runs ~6 tok/s
Qwen 2.5 14B 14B Q4_K_M 9.9 GB Runs ~7 tok/s
Qwen 2.5 Coder 14B 14B Q4_K_M 12 GB Runs ~6 tok/s
Qwen 3 14B 14B Q4_K_M 12 GB Runs ~6 tok/s
Qwen 3.5 35B A3B 35B Q4_K_M 12 GB Runs ~6 tok/s
Codestral 22B 22B Q4_K_M 14.7 GB Runs (tight) ~5 tok/s
StarCoder2 15B 15B Q8_0 17 GB CPU Offload ~1 tok/s
Devstral 24B 24B Q4_K_M 17 GB CPU Offload ~1 tok/s
Magistral Small 24B 24B Q4_K_M 17 GB CPU Offload ~1 tok/s
Mistral Small 3.1 24B 24B Q4_K_M 18 GB CPU Offload ~1 tok/s
Gemma 4 26B 26B Q4_K_M 20 GB CPU Offload ~1 tok/s
Gemma 2 27B 27B Q4_K_M 17.7 GB CPU Offload ~1 tok/s
Gemma 3 27B 27B Q4_K_M 20 GB CPU Offload ~1 tok/s
Qwen 3.5 27B 27B Q4_K_M 19 GB CPU Offload ~1 tok/s
Qwen 3 30B-A3B (MoE) 30B Q4_K_M 22 GB CPU Offload ~1 tok/s
Gemma 4 31B 31B Q4_K_M 22 GB CPU Offload ~1 tok/s
Aya Expanse 32B 32B Q4_K_M 22 GB CPU Offload ~1 tok/s
Cogito 32B 32B Q4_K_M 21.5 GB CPU Offload ~1 tok/s
DeepSeek R1 32B 32B Q4_K_M 20.7 GB CPU Offload ~1 tok/s
Qwen 2.5 32B 32B Q4_K_M 20.7 GB CPU Offload ~1 tok/s
Qwen 2.5 Coder 32B 32B Q4_K_M 23 GB CPU Offload ~1 tok/s
Qwen 3 32B 32B Q4_K_M 23 GB CPU Offload ~1 tok/s
QwQ 32B 32B Q4_K_M 21.5 GB CPU Offload ~1 tok/s
Command R 35B 35B Q4_K_M 22.5 GB CPU Offload ~1 tok/s
23 model(s) are too large for this hardware.