Mac mini M4 16GB
16 GB unified · 120 GB/s
Prices
Every retailer we track in the US, cheapest first. Buy links may earn us a commission.
No retailer in this market lists it right now.
What it runs
Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @32k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Gemma 4 12B | Q5_K_M | fits | 9.4 GB | 90k148k with q8 cache | 8tok/sest. | 56 tok/s | – |
| Qwen 3.5 9B Alibaba Qwen | Q6_K | fits | 8.8 GB | 83k138k with q8 cache | 9tok/sest. | 70 tok/s | – |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q4_K_M | fits | 10.0 GB | 36k67k with q8 cache | 8tok/sest. | 58 tok/s | – |
| Qwen3 8B Alibaba Qwen | Q4_K_M | fits | 10.0 GB | 36k40k with q8 cache | 8tok/sest. | 58 tok/s | – |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 6.0 GB | 158k256k with q8 cache | 14tok/sest. | 131 tok/s | chat |
| Ministral 3 8B Mistral AI | Q5_K_M | fits | 10.7 GB | 32k58k with q8 cache | 7tok/sest. | 56 tok/s | – |
| Gemma 4 E4B | Q8_0 | fits | 9.3 GB | 73k120k with q8 cache | 9tok/sest. | 88 tok/s | – |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 10.7 GB | 32k55k with q8 cache | 18tok/sest. | 288 tok/s | chat |
| Llama 3.1 8B Meta | Q5_K_M | fits | 10.1 GB | 36k65k with q8 cache | 8tok/sest. | 61 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 93.7 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 102.5 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 75.1 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 78.7 GB | – | – | – | – |
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | won't run | 18.3 GB | – | – | – | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | won't run | 40.6 GB | – | – | – | – |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | won't run | 18.6 GB | – | – | – | – |
| Gemma 4 31B | Q4_K_M | won't run | 21.1 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 52.1 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 46.8 GB | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 61.0 GB | – | – | – | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | won't run | 38.9 GB | – | – | – | – |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | won't run | 18.5 GB | – | – | – | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q4_K_M | won't run | 22.1 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 48.7 GB | – | – | – | – |
| Gemma 4 26B-A4B | UD-Q4_K_M | won't run | 17.4 GB | – | – | – | – |
| Devstral Small 2 24B Mistral AI | Q4_K_M | won't run | 19.1 GB | – | – | – | – |
| GLM 4.7 Flash Z.ai | Q4_K_M | won't run | 19.5 GB | – | – | – | – |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | won't run | 22.0 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 46.8 GB | – | – | – | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | won't run | 33.6 GB | – | – | – | – |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | won't run | 29.1 GB | – | – | – | – |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | won't run | 21.1 GB | – | – | – | – |
| gpt-oss 20B OpenAI | MXFP4 | won't run | 12.8 GB | – | – | – | – |
| Qwen3 32B Alibaba Qwen | Q4_K_M | won't run | 27.2 GB | – | – | – | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | won't run | 27.3 GB | – | – | – | – |
| Gemma 3 27B | Q4_K_M | won't run | 19.1 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 50.4 GB | – | – | – | – |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | won't run | 19.1 GB | – | – | – | – |
| Ministral 3 14B Mistral AI | Q4_K_M | won't run | 13.5 GB | 14k27k with q8 cache | – | – | – |
| Qwen3 14B Alibaba Qwen | Q4_K_M | won't run | 14.2 GB | 10k19k with q8 cache | – | – | – |
| Phi-4 14B Microsoft | Q4_K_M | won't run | 15.3 GB | 9k16k with q8 cache | – | – | – |
| Granite 4.2 8B IBM | Q4_K_M | won't run | 10.9 GB | 30k55k with q8 cache | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- Chip
- Apple M4 (10-core GPU)
- Memory bus
- 128-bit
- Memory bandwidth
- 120 GB/s
- FP16 compute
- 3.76 TFLOPS
- Software
- Metal
- Unified memory
- 16 GB
- GPU can use by default
- 10.7 GB
- GPU can use, tuned
- 10.666666666666666 GB
- Operating system
- macos
- Processor
- M4 10-core
- Storage
- 256 GB