Mac Studio M3 Ultra 512GB
$23,000
Parts
A complete machine needs no part checks.
| Component | Selection | Price | Where | Buy |
|---|---|---|---|---|
| Machine | Mac Studio M3 Ultra 512GB 512 GB unified · 819 GB/s | $23,000 | eBay | Buy |
| Total | $23,000 | |||
What this build runs
The most precise quant that fits, at 64k context. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @64k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash DeepSeek | MXFP4 | fits | 151.6 GB | 1024k | 19tok/sest. | 50 tok/s | chat, coding |
| GLM 5.3 Flash Z.ai | Q8_0 | fits | 319.4 GB | 1024k | 12tok/sest. | 76 tok/s | – |
| Qwen 3.8 Flash Next Alibaba Qwen | Q8_0 | fits | 177.9 GB | 256k | 5tok/sest. | 84 tok/s | – |
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 32.2 GB | 256k | 16tok/sest. | 164 tok/s | chat |
| MiniMax M2.7 MiniMax | Q8_0 | fits | 242.9 GB | 200k | 11tok/sest. | 156 tok/s | chat |
| Qwen 3.5 122B-A10B Alibaba Qwen | Q8_0 | fits | 123.6 GB | 256k | 26tok/sest. | 341 tok/s | chat, coding |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 31.7 GB | 256k | 16tok/sest. | 164 tok/s | chat |
| gpt-oss 120B OpenAI | MXFP4 | fits | 62.3 GB | 128k | 58tok/sest. | 528 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder Next Alibaba Qwen | Q8_0 | fits | 81.5 GB | 256k | 55tok/sest. | 789 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | Q8_0 | fits | 121.3 GB | 256k | 24tok/sest. | 396 tok/s | chat, coding, long documents |
| Gemma 4 31B | Q8_0 | fits | 37.2 GB | 256k | 14tok/sest. | 149 tok/s | chat |
| Mistral Small 4 119B Mistral AI | Q8_0 | fits | 120.2 GB | 1024k | 36tok/sest. | 335 tok/s | chat, coding |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 36.7 GB | 256k | 71tok/sest. | 985 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 31.7 GB | 256k | 16tok/sest. | 164 tok/s | chat |
| Gemma 4 26B-A4B | Q8_0 | fits | 27.4 GB | 256k | 56tok/sest. | 1009 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q8_0 | fits | 121.9 GB | 128k | 11tok/sest. | 104 tok/s | chat |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 36.7 GB | 256k | 71tok/sest. | 985 tok/s | chat, coding, agents, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q8_0 | fits | 81.5 GB | 256k | 66tok/sest. | 900 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 33.9 GB | 198k | 36tok/sest. | 489 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 34.3 GB | 384k | 15tok/sest. | 161 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 34.0 GB | 256k | 85tok/sest. | 1215 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q8_0 | fits | 50.2 GB | 1024k | 85tok/sest. | 791 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 13.8 GB | 128k | 79tok/sest. | 754 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 37.2 GB | 256k | 33tok/sest. | 353 tok/s | chat, coding, agents |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 49.4 GB | 40k | 10tok/sest. | 83 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 14.1 GB | 256k | 38tok/sest. | 388 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 11.9 GB | 256k | 45tok/sest. | 475 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q8_0 | fits | 33.1 GB | 128k | 15tok/sest. | 183 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 34.3 GB | 128k | 15tok/sest. | 161 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 49.4 GB | 128k | 10tok/sest. | 103 tok/s | – |
| Llama 3.3 70B Meta | Q8_0 | fits | 90.8 GB | 128k | 6tok/sest. | 49 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 24.3 GB | 256k | 21tok/sest. | 227 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 25.6 GB | 40k | 20tok/sest. | 199 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.1 GB | 128k | 29tok/sest. | 314 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.1 GB | 40k | 29tok/sest. | 314 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q8_0 | fits | 28.0 GB | 16k | 18tok/sest. | 199 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.2 GB | 256k | 80tok/sest. | 823 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 17.9 GB | 256k | 29tok/sest. | 310 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 19.7 GB | 128k | 27tok/sest. | 287 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 10.4 GB | 128k | 53tok/sest. | 622 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 12.4 GB | 125k | 75tok/sest. | 1327 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 15.1 GB | 128k | 35tok/sest. | 337 tok/s | chat, coding |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 2.2 GB | 32k | 398tok/sest. | 2942 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.5 GB | 256k | 325tok/sest. | 3336 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 3.1 GB | 256k | 236tok/sest. | 1819 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 4.5 GB | 128k | 141tok/sest. | 1219 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 6.1 GB | 128k | 97tok/sest. | 687 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 13.9 GB | 128k | 88tok/sest. | 1229 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 7.4 GB | 128k | 77tok/sest. | 833 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 7.4 GB | 32k | 77tok/sest. | 783 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 19.5 GB | 128k | 60tok/sest. | 845 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 9.3 GB | 128k | 59tok/sest. | 523 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 9.6 GB | 128k | 58tok/sest. | 540 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 12.0 GB | 128k | 45tok/sest. | 395 tok/s | chat, coding |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 29.7 GB | 128k | 43tok/sest. | 760 tok/s | chat, coding, agents, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 12.8 GB | 128k | 42tok/sest. | 266 tok/s | chat, coding |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 14.4 GB | 64k | 37tok/sest. | 266 tok/s | chat, coding |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 16.9 GB | 128k | 31tok/sest. | 337 tok/s | chat, coding |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 17.9 GB | 256k | 29tok/sest. | 310 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 27.6 GB | 128k | 19tok/sest. | 181 tok/s | chat, coding |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 34.3 GB | 128k | 15tok/sest. | 163 tok/s | chat |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 34.3 GB | 40k | 15tok/sest. | 163 tok/s | chat |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 34.3 GB | 40k | 15tok/sest. | 163 tok/s | chat |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 34.3 GB | 128k | 15tok/sest. | 161 tok/s | chat |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | fits | 152.0 GB | 1024k | 14tok/sest. | 44 tok/s | chat |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | fits | 160.8 GB | 1024k | 13tok/sest. | 44 tok/s | chat |
| DeepSeek R1 DeepSeek | Q4_K_M | fits | 381.9 GB | 92k160k with q8 cache | 12tok/sest. | 41 tok/s | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | fits | 382.4 GB | 86k151k with q8 cache | 12tok/sest. | 41 tok/s | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | fits | 381.9 GB | 92k160k with q8 cache | 12tok/sest. | 41 tok/s | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | fits | 382.8 GB | 80k140k with q8 cache | 12tok/sest. | 41 tok/s | – |
| GLM 4.5V Z.ai | Q8_0 | fits | 118.3 GB | 64k | 12tok/sest. | 109 tok/s | chat |
| GLM 4.6V Z.ai | Q8_0 | fits | 118.3 GB | 128k | 12tok/sest. | 109 tok/s | chat |
| MiniMax M3 MiniMax | UD-Q6_K | fits | 339.4 GB | 426k770k with q8 cache | 12tok/sest. | 101 tok/s | chat |
| DeepSeek V3.2 DeepSeek | Q4_K_M | fits | 382.8 GB | 80k140k with q8 cache | 12tok/sest. | 41 tok/s | – |
| MiniMax M2 MiniMax | Q8_0 | fits | 242.9 GB | 192k | 11tok/sest. | 156 tok/s | chat |
| MiniMax M2.1 MiniMax | Q8_0 | fits | 242.9 GB | 192k | 11tok/sest. | 156 tok/s | chat |
| MiniMax M2.5 MiniMax | Q8_0 | fits | 242.9 GB | 192k | 11tok/sest. | 156 tok/s | chat |
| granite 4.2 30b IBM | Q8_0 | fits | 46.0 GB | 128k | 11tok/sest. | 121 tok/s | chat |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q8_0 | fits | 90.8 GB | 128k | 6tok/sest. | 49 tok/s | – |
| GLM 4.7 Z.ai | Q8_0 | fits | 378.8 GB | 78k145k with q8 cache | 5tok/sest. | 49 tok/s | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | fits | 146.7 GB | 256k | 3tok/sest. | 29 tok/s | – |
| Mistral Medium 3.5 128B Mistral AI | Q8_0 | fits | 146.7 GB | 256k | 3tok/sest. | 28 tok/s | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 426.4 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 440.3 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 752.8 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 583.4 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 583.8 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 583.8 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 583.8 GB | – | – | – | – |