Mac mini M4 Pro 64GB
$2,900
Parts
A complete machine needs no part checks.
| Component | Selection | Price | Where | Buy |
|---|---|---|---|---|
| Machine | Mac mini M4 Pro 64GB 64 GB unified · 273 GB/s | $2,900 | eBay | Buy |
| Total | $2,900 | |||
What this build runs
The most precise quant that fits, at 128k context. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @128k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 36.5 GB | 256k | 5tok/sest. | 40 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | fits | 43.5 GB | 256k | 16tok/sest. | 71 tok/s | chat, coding |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 36.1 GB | 256k | 5tok/sest. | 40 tok/s | – |
| Gemma 4 31B | Q8_0 | fits | 42.5 GB | 193k256k with q8 cache | 4tok/sest. | 38 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | fits | 41.6 GB | 357k568k with q8 cache | 20tok/sest. | 61 tok/s | chat, coding |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 38.3 GB | 256k | 18tok/sest. | 193 tok/s | chat, coding |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 36.1 GB | 256k | 5tok/sest. | 40 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 29.1 GB | 256k | 15tok/sest. | 234 tok/s | chat, coding |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 38.3 GB | 256k | 18tok/sest. | 193 tok/s | chat, coding |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 37.6 GB | 198k | 9tok/sest. | 91 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 44.7 GB | 148k270k with q8 cache | 4tok/sest. | 36 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 34.7 GB | 256k | 26tok/sest. | 260 tok/s | chat, coding |
| Kimi Linear 48B-A3B Moonshot AI | Q6_K | fits | 40.1 GB | 714k973k with q8 cache | 30tok/sest. | 145 tok/s | chat, coding |
| gpt-oss 20B OpenAI | MXFP4 | fits | 15.6 GB | 128k | 19tok/sest. | 152 tok/s | chat, coding |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 43.6 GB | 172k256k with q8 cache | 7tok/sest. | 56 tok/s | chat |
| Gemma 4 12B | Q8_0 | fits | 15.5 GB | 256k | 12tok/sest. | 97 tok/s | – |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 14.3 GB | 256k | 13tok/sest. | 116 tok/s | chat |
| Gemma 3 27B | Q8_0 | fits | 38.5 GB | 128k | 4tok/sest. | 49 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 44.7 GB | 128k | 4tok/sest. | 36 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 34.7 GB | 209k256k with q8 cache | 5tok/sest. | 46 tok/s | – |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 36.0 GB | 40k | 5tok/sest. | 39 tok/s | – |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 27.5 GB | 128k | 6tok/sest. | 59 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 27.5 GB | 40k | 6tok/sest. | 59 tok/s | chat |
| Phi-4 14B Microsoft | Q8_0 | fits | 40.9 GB | 16k | 4tok/sest. | 39 tok/s | – |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 9.6 GB | 256k | 20tok/sest. | 181 tok/s | chat, coding |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 26.8 GB | 256k | 7tok/sest. | 60 tok/s | chat |
| Granite 4.2 8B IBM | Q8_0 | fits | 30.1 GB | 128k | 6tok/sest. | 53 tok/s | chat |
| Gemma 4 E4B | Q8_0 | fits | 12.5 GB | 128k | 15tok/sest. | 162 tok/s | chat |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 15.7 GB | 125k | 14tok/sest. | 217 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q6_K | fits | 23.5 GB | 128k | 8tok/sest. | 64 tok/s | chat |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 3.3 GB | 32k | 83tok/sest. | 488 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 3.6 GB | 256k | 73tok/sest. | 651 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 4.2 GB | 256k | 58tok/sest. | 416 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 6.6 GB | 128k | 31tok/sest. | 218 tok/s | chat, coding |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 15.2 GB | 128k | 23tok/sest. | 251 tok/s | chat, coding |
| MiniCPM5 2B openbmb | Q8_0 | fits | 9.1 GB | 128k | 21tok/sest. | 117 tok/s | chat, coding |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 11.5 GB | 128k | 16tok/sest. | 150 tok/s | chat, coding |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 11.5 GB | 32k | 16tok/sest. | 145 tok/s | chat, coding |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 21.7 GB | 128k | 15tok/sest. | 158 tok/s | chat, coding |
| granite vision 4.1 4b IBM | Q8_0 | fits | 14.7 GB | 128k | 12tok/sest. | 93 tok/s | chat, coding |
| granite 4.2 3b IBM | Q8_0 | fits | 15.0 GB | 128k | 12tok/sest. | 95 tok/s | chat, coding |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 15.7 GB | 128k | 12tok/sest. | 51 tok/s | chat |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 15.9 GB | 128k | 11tok/sest. | 78 tok/s | chat |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 17.3 GB | 64k | 10tok/sest. | 51 tok/s | – |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 35.1 GB | 128k | 8tok/sest. | 127 tok/s | chat, coding |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 25.3 GB | 128k | 7tok/sest. | 64 tok/s | chat |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 26.8 GB | 256k | 7tok/sest. | 60 tok/s | chat |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 40.0 GB | 128k | 4tok/sest. | 34 tok/s | – |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 44.7 GB | 128k | 4tok/sest. | 36 tok/s | – |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 44.7 GB | 40k | 4tok/sest. | 36 tok/s | – |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 44.7 GB | 40k | 4tok/sest. | 36 tok/s | – |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 44.7 GB | 128k | 4tok/sest. | 36 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 102.3 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 104.1 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 77.9 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 102.5 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 53.4 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 49.6 GB | 72k116k with q8 cache | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 64.3 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 66.6 GB | 27k51k with q8 cache | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 49.6 GB | 73k117k with q8 cache | – | – | – |
| Qwen3 32B Alibaba Qwen | Q4_K_M | won't run | 51.8 GB | 40k | – | – | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | won't run | 51.8 GB | 112k128k with q8 cache | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 81.0 GB | 24k45k with q8 cache | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 386.6 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 387.1 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 81.0 GB | 24k45k with q8 cache | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 386.6 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 387.5 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 387.5 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 157.7 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 166.5 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | won't run | 169.1 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 83.6 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 90.0 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 248.9 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 432.3 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 446.2 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 758.6 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 588.1 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 588.5 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 588.5 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 588.5 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 161.2 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 161.2 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 147.6 GB | – | – | – | – |
| MiniMax M3 MiniMax | UD-Q4_K_M | won't run | 263.1 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 115.1 GB | – | – | – | – |
| granite 4.2 30b IBM | Q4_K_M | won't run | 50.1 GB | 119k128k with q8 cache | – | – | – |