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 8k context. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @8k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 28.3 GB | 256k | 6tok/sest. | 57 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | fits | 39.9 GB | 256k | 29tok/sest. | 150 tok/s | chat, coding |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 27.9 GB | 256k | 6tok/sest. | 57 tok/s | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | fits | 46.1 GB | 72k116k with q8 cache | 40tok/sest. | 378 tok/s | chat, coding |
| Gemma 4 31B | Q8_0 | fits | 32.4 GB | 193k256k with q8 cache | 5tok/sest. | 49 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | fits | 38.3 GB | 357k568k with q8 cache | 42tok/sest. | 195 tok/s | chat, coding |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.2 GB | 256k | 32tok/sest. | 485 tok/s | chat, coding |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 27.9 GB | 256k | 6tok/sest. | 57 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 26.0 GB | 256k | 23tok/sest. | 369 tok/s | chat, coding |
| GLM 4.5 Air Z.ai | Q2_K | fits | 44.3 GB | 27k51k with q8 cache | 13tok/sest. | 75 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | fits | 46.1 GB | 73k117k with q8 cache | 52tok/sest. | 475 tok/s | chat, coding |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.2 GB | 256k | 32tok/sest. | 485 tok/s | chat, coding |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 30.7 GB | 198k | 19tok/sest. | 271 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 25.2 GB | 148k270k with q8 cache | 7tok/sest. | 64 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 33.3 GB | 256k | 31tok/sest. | 505 tok/s | chat, coding |
| Kimi Linear 48B-A3B Moonshot AI | Q6_K | fits | 38.4 GB | 714k973k with q8 cache | 41tok/sest. | 461 tok/s | chat, coding |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.1 GB | 128k | 40tok/sest. | 351 tok/s | chat, coding |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 31.6 GB | 172k256k with q8 cache | 27tok/sest. | 351 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 35.1 GB | 40k | 5tok/sest. | 44 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 12.9 GB | 256k | 14tok/sest. | 129 tok/s | – |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 9.8 GB | 256k | 18tok/sest. | 163 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 25.2 GB | 128k | 7tok/sest. | 64 tok/s | – |
| Gemma 3 27B | Q8_0 | fits | 28.4 GB | 128k | 6tok/sest. | 57 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 35.1 GB | 58k107k with q8 cache | 5tok/sest. | 46 tok/s | – |
| Llama 3.3 70B Meta | Q4_K_M | fits | 42.7 GB | 24k45k with q8 cache | 4tok/sest. | 21 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 15.3 GB | 209k256k with q8 cache | 11tok/sest. | 106 tok/s | – |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 16.5 GB | 40k | 10tok/sest. | 98 tok/s | – |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 9.9 GB | 128k | 18tok/sest. | 172 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 9.9 GB | 40k | 18tok/sest. | 172 tok/s | chat |
| Phi-4 14B Microsoft | Q8_0 | fits | 16.7 GB | 16k | 10tok/sest. | 99 tok/s | – |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.1 GB | 256k | 37tok/sest. | 328 tok/s | chat, coding |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.1 GB | 256k | 17tok/sest. | 161 tok/s | chat |
| Granite 4.2 8B IBM | Q8_0 | fits | 10.6 GB | 128k | 17tok/sest. | 160 tok/s | chat |
| Gemma 4 E4B | Q8_0 | fits | 8.5 GB | 128k | 21tok/sest. | 197 tok/s | chat |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.4 GB | 125k | 73tok/sest. | 1152 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q6_K | fits | 7.8 GB | 128k | 23tok/sest. | 178 tok/s | chat |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.2 GB | 32k | 281tok/sest. | 2411 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 1.5 GB | 256k | 191tok/sest. | 1659 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.1 GB | 256k | 114tok/sest. | 681 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 2.6 GB | 128k | 83tok/sest. | 759 tok/s | chat, coding |
| MiniCPM5 2B openbmb | Q8_0 | fits | 3.5 GB | 128k | 59tok/sest. | 502 tok/s | chat, coding |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 3.8 GB | 128k | 53tok/sest. | 505 tok/s | chat, coding |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 3.8 GB | 32k | 53tok/sest. | 446 tok/s | chat, coding |
| granite vision 4.1 4b IBM | Q8_0 | fits | 4.6 GB | 128k | 41tok/sest. | 334 tok/s | chat, coding |
| granite 4.2 3b IBM | Q8_0 | fits | 4.9 GB | 128k | 39tok/sest. | 359 tok/s | chat, coding |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 25.0 GB | 128k | 38tok/sest. | 605 tok/s | chat, coding |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 12.8 GB | 128k | 38tok/sest. | 555 tok/s | chat, coding |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 17.5 GB | 128k | 30tok/sest. | 468 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 8.6 GB | 128k | 21tok/sest. | 192 tok/s | chat |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 9.6 GB | 128k | 19tok/sest. | 178 tok/s | chat |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 10.1 GB | 256k | 17tok/sest. | 161 tok/s | chat |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 10.3 GB | 128k | 17tok/sest. | 139 tok/s | chat |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 11.9 GB | 64k | 15tok/sest. | 139 tok/s | – |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 16.8 GB | 128k | 10tok/sest. | 96 tok/s | – |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 25.2 GB | 128k | 7tok/sest. | 65 tok/s | – |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 25.2 GB | 40k | 7tok/sest. | 65 tok/s | – |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 25.2 GB | 40k | 7tok/sest. | 65 tok/s | – |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 25.2 GB | 128k | 7tok/sest. | 64 tok/s | – |
| granite 4.2 30b IBM | Q8_0 | fits | 31.6 GB | 72k128k with q8 cache | 5tok/sest. | 51 tok/s | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | fits | 42.7 GB | 24k45k with q8 cache | 4tok/sest. | 21 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 91.5 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 102.1 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 74.4 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 72.7 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 51.8 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 59.4 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 377.8 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 378.3 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 377.8 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 378.7 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 378.7 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 147.0 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 155.7 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | won't run | 127.1 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 61.3 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 67.7 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 205.1 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 421.3 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 435.2 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 747.7 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 579.3 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 579.8 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 579.8 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 579.8 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 131.4 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 131.4 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 117.9 GB | – | – | – | – |
| MiniMax M3 MiniMax | UD-Q4_K_M | won't run | 248.3 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 73.2 GB | – | – | – | – |