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 32k context. 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 | 256k | 6tok/sest. | 52 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | fits | 40.6 GB | 256k | 25tok/sest. | 122 tok/s | chat, coding |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 29.6 GB | 256k | 6tok/sest. | 52 tok/s | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | fits | 46.8 GB | 72k116k with q8 cache | 33tok/sest. | 295 tok/s | chat, coding |
| Gemma 4 31B | Q8_0 | fits | 34.5 GB | 193k256k with q8 cache | 5tok/sest. | 46 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | fits | 38.9 GB | 357k568k with q8 cache | 34tok/sest. | 136 tok/s | chat, coding |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.8 GB | 256k | 28tok/sest. | 372 tok/s | chat, coding |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 29.6 GB | 256k | 6tok/sest. | 52 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 26.6 GB | 256k | 21tok/sest. | 331 tok/s | chat, coding |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | fits | 46.8 GB | 73k117k with q8 cache | 40tok/sest. | 351 tok/s | chat, coding |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.8 GB | 256k | 28tok/sest. | 372 tok/s | chat, coding |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 32.1 GB | 198k | 15tok/sest. | 194 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 29.1 GB | 148k270k with q8 cache | 6tok/sest. | 55 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 33.6 GB | 256k | 30tok/sest. | 425 tok/s | chat, coding |
| Kimi Linear 48B-A3B Moonshot AI | Q6_K | fits | 38.8 GB | 714k973k with q8 cache | 38tok/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 | 172k256k with q8 cache | 17tok/sest. | 171 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 41.2 GB | 40k | 4tok/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 | 128k | 6tok/sest. | 55 tok/s | – |
| Gemma 3 27B | Q8_0 | fits | 30.4 GB | 128k | 6tok/sest. | 55 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 41.2 GB | 58k107k with q8 cache | 4tok/sest. | 37 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 19.2 GB | 209k256k 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 | 256k | 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 |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.7 GB | 32k | 190tok/sest. | 1348 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 1.9 GB | 256k | 144tok/sest. | 1266 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.5 GB | 256k | 96tok/sest. | 604 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 3.4 GB | 128k | 63tok/sest. | 507 tok/s | chat, coding |
| MiniCPM5 2B openbmb | Q8_0 | fits | 4.6 GB | 128k | 43tok/sest. | 303 tok/s | chat, coding |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 5.3 GB | 128k | 36tok/sest. | 343 tok/s | chat, coding |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 5.3 GB | 32k | 36tok/sest. | 315 tok/s | chat, coding |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 13.3 GB | 128k | 34tok/sest. | 447 tok/s | chat, coding |
| granite vision 4.1 4b IBM | Q8_0 | fits | 6.7 GB | 128k | 28tok/sest. | 220 tok/s | chat, coding |
| granite 4.2 3b IBM | Q8_0 | fits | 6.9 GB | 128k | 27tok/sest. | 230 tok/s | chat, coding |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 18.3 GB | 128k | 25tok/sest. | 336 tok/s | chat, coding |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 27.0 GB | 128k | 22tok/sest. | 345 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 10.1 GB | 128k | 18tok/sest. | 148 tok/s | chat |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 11.4 GB | 128k | 16tok/sest. | 103 tok/s | chat |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 12.7 GB | 128k | 14tok/sest. | 131 tok/s | chat |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 13.0 GB | 64k | 14tok/sest. | 103 tok/s | – |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 13.4 GB | 256k | 13tok/sest. | 120 tok/s | chat |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 21.4 GB | 128k | 8tok/sest. | 71 tok/s | – |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 29.1 GB | 128k | 6tok/sest. | 56 tok/s | – |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 29.1 GB | 40k | 6tok/sest. | 56 tok/s | – |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 29.1 GB | 40k | 6tok/sest. | 56 tok/s | – |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 29.1 GB | 128k | 6tok/sest. | 55 tok/s | – |
| granite 4.2 30b IBM | Q8_0 | fits | 37.8 GB | 72k128k with q8 cache | 5tok/sest. | 43 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 | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 52.1 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 60.4 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 48.7 GB | 27k51k with q8 cache | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 50.4 GB | 24k45k with q8 cache | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 379.6 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 380.1 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 50.4 GB | 24k45k with q8 cache | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 379.6 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 380.5 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 380.5 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 149.1 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 157.9 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | won't run | 135.5 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 65.8 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 72.1 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 213.9 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 423.5 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 437.4 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 749.9 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 581.1 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 581.5 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 581.5 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 581.5 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 137.4 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 137.4 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 123.8 GB | – | – | – | – |
| MiniMax M3 MiniMax | UD-Q4_K_M | won't run | 251.3 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 81.5 GB | – | – | – | – |