Mac mini M4 Pro 48GB
48 GB unified · 273 GB/s
Prices
Every retailer we track in the UK, 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 |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 30.0 GB | 120k210k with q8 cache | 6tok/sest. | 52 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 29.6 GB | 126k220k with q8 cache | 6tok/sest. | 52 tok/s | – |
| Gemma 4 31B | Q8_0 | fits | 34.5 GB | 50k96k with q8 cache | 5tok/sest. | 46 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.8 GB | 38k59k with q8 cache | 28tok/sest. | 372 tok/s | chat, coding |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 29.6 GB | 126k220k with q8 cache | 6tok/sest. | 52 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 26.6 GB | 256k | 21tok/sest. | 331 tok/s | chat, coding |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.8 GB | 38k59k with q8 cache | 28tok/sest. | 372 tok/s | chat, coding |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 32.1 GB | 99k172k with q8 cache | 15tok/sest. | 194 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 29.1 GB | 74k135k with q8 cache | 6tok/sest. | 55 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 33.6 GB | 235k256k with q8 cache | 30tok/sest. | 425 tok/s | chat, coding |
| Kimi Linear 48B-A3B Moonshot AI | Q5_K_M | fits | 33.8 GB | 197k268k with q8 cache | 44tok/sest. | 321 tok/s | chat, coding |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.8 GB | 128k | 33tok/sest. | 278 tok/s | chat, coding |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 34.0 GB | 51k92k with q8 cache | 17tok/sest. | 171 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q6_K | fits | 33.8 GB | 40k | 5tok/sest. | 32 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 13.4 GB | 256k | 13tok/sest. | 121 tok/s | – |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.7 GB | 256k | 17tok/sest. | 151 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 29.1 GB | 74k128k with q8 cache | 6tok/sest. | 55 tok/s | – |
| Gemma 3 27B | Q8_0 | fits | 30.4 GB | 98k128k with q8 cache | 6tok/sest. | 55 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q6_K | fits | 33.8 GB | 40k74k with q8 cache | 5tok/sest. | 37 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 19.2 GB | 135k247k with q8 cache | 9tok/sest. | 84 tok/s | – |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 20.4 GB | 40k | 8tok/sest. | 75 tok/s | – |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 13.4 GB | 128k | 13tok/sest. | 124 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 13.4 GB | 40k | 13tok/sest. | 124 tok/s | chat |
| Phi-4 14B Microsoft | Q8_0 | fits | 21.5 GB | 16k | 8tok/sest. | 76 tok/s | – |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 6.0 GB | 256k | 32tok/sest. | 282 tok/s | chat, coding |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 13.4 GB | 194k256k with q8 cache | 13tok/sest. | 120 tok/s | chat |
| Granite 4.2 8B IBM | Q8_0 | fits | 14.5 GB | 128k | 12tok/sest. | 114 tok/s | chat |
| Gemma 4 E4B | Q8_0 | fits | 9.3 GB | 128k | 19tok/sest. | 189 tok/s | chat |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 10.7 GB | 125k | 40tok/sest. | 619 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q6_K | fits | 10.9 GB | 128k | 16tok/sest. | 131 tok/s | chat |
| 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 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | won't run | 40.6 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 | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 48.7 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 46.8 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 50.4 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- Chip
- Apple M4 Pro (20-core GPU)
- Memory bus
- 256-bit
- Memory bandwidth
- 273 GB/s
- FP16 compute
- 8.08 TFLOPS
- Software
- Metal
- Unified memory
- 48 GB
- GPU can use by default
- 36 GB
- GPU can use, tuned
- 40 GB
- Operating system
- macos
- Processor
- M4 Pro 14-core
- Storage
- 512 GB