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 128k context. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @128k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash DeepSeek | MXFP4 | fits | 157.4 GB | 1024k | 14tok/sest. | 27 tok/s | chat, coding |
| GLM 5.3 Flash Z.ai | Q8_0 | fits | 320.4 GB | 1024k | 11tok/sest. | 46 tok/s | – |
| Qwen 3.8 Flash Next Alibaba Qwen | Q8_0 | fits | 179.8 GB | 256k | 5tok/sest. | 79 tok/s | – |
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 36.5 GB | 256k | 14tok/sest. | 138 tok/s | chat |
| MiniMax M2.7 MiniMax | Q8_0 | fits | 258.8 GB | 200k | 7tok/sest. | 92 tok/s | chat |
| Qwen 3.5 122B-A10B Alibaba Qwen | Q8_0 | fits | 125.4 GB | 256k | 23tok/sest. | 245 tok/s | chat, coding |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 36.1 GB | 256k | 14tok/sest. | 138 tok/s | chat |
| Qwen3 Coder Next Alibaba Qwen | Q8_0 | fits | 83.4 GB | 256k | 43tok/sest. | 543 tok/s | chat, coding, agents, long documents |
| gpt-oss 120B OpenAI | MXFP4 | fits | 64.9 GB | 128k | 40tok/sest. | 363 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | Q8_0 | fits | 122.2 GB | 256k | 23tok/sest. | 344 tok/s | chat, coding, long documents |
| Gemma 4 31B | Q8_0 | fits | 42.5 GB | 256k | 12tok/sest. | 131 tok/s | chat |
| Mistral Small 4 119B Mistral AI | Q8_0 | fits | 121.9 GB | 1024k | 30tok/sest. | 212 tok/s | chat, coding |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 38.3 GB | 256k | 55tok/sest. | 669 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 36.1 GB | 256k | 14tok/sest. | 138 tok/s | chat |
| Gemma 4 26B-A4B | Q8_0 | fits | 29.1 GB | 256k | 45tok/sest. | 812 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q8_0 | fits | 133.7 GB | 128k | 8tok/sest. | 62 tok/s | chat |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 38.3 GB | 256k | 55tok/sest. | 669 tok/s | chat, coding, agents, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q8_0 | fits | 83.4 GB | 256k | 50tok/sest. | 593 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 37.6 GB | 198k | 26tok/sest. | 316 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 44.7 GB | 384k | 11tok/sest. | 123 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 34.7 GB | 256k | 76tok/sest. | 900 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q8_0 | fits | 51.0 GB | 1024k | 75tok/sest. | 502 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 15.6 GB | 128k | 57tok/sest. | 526 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 43.6 GB | 256k | 20tok/sest. | 195 tok/s | chat, coding, agents |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 65.8 GB | 40k | 8tok/sest. | 55 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 15.5 GB | 256k | 35tok/sest. | 338 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 14.3 GB | 256k | 38tok/sest. | 402 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q8_0 | fits | 38.5 GB | 128k | 13tok/sest. | 169 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 44.7 GB | 128k | 11tok/sest. | 123 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 65.8 GB | 128k | 8tok/sest. | 74 tok/s | – |
| Llama 3.3 70B Meta | Q8_0 | fits | 111.2 GB | 128k | 5tok/sest. | 36 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 34.7 GB | 256k | 15tok/sest. | 158 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 36.0 GB | 40k | 14tok/sest. | 135 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 27.5 GB | 128k | 19tok/sest. | 204 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 27.5 GB | 40k | 19tok/sest. | 204 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q8_0 | fits | 40.9 GB | 16k | 13tok/sest. | 135 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 9.6 GB | 256k | 60tok/sest. | 625 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 26.8 GB | 256k | 20tok/sest. | 206 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 30.1 GB | 128k | 17tok/sest. | 185 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 12.5 GB | 128k | 44tok/sest. | 563 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 15.7 GB | 125k | 43tok/sest. | 752 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 23.5 GB | 128k | 22tok/sest. | 222 tok/s | chat, coding |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 3.3 GB | 32k | 249tok/sest. | 1691 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 3.6 GB | 256k | 218tok/sest. | 2254 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 4.2 GB | 256k | 174tok/sest. | 1442 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 6.6 GB | 128k | 94tok/sest. | 755 tok/s | chat, coding, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 15.2 GB | 128k | 70tok/sest. | 870 tok/s | chat, coding, agents, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 9.1 GB | 128k | 64tok/sest. | 406 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 11.5 GB | 128k | 49tok/sest. | 521 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 11.5 GB | 32k | 49tok/sest. | 501 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 21.7 GB | 128k | 44tok/sest. | 547 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 14.7 GB | 128k | 37tok/sest. | 322 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 15.0 GB | 128k | 36tok/sest. | 328 tok/s | chat, coding, agents, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 15.7 GB | 128k | 35tok/sest. | 176 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 15.9 GB | 128k | 34tok/sest. | 270 tok/s | chat, coding |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 17.3 GB | 64k | 31tok/sest. | 176 tok/s | chat, coding |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 35.1 GB | 128k | 25tok/sest. | 440 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 25.3 GB | 128k | 21tok/sest. | 222 tok/s | chat, coding |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 26.8 GB | 256k | 20tok/sest. | 206 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 40.0 GB | 128k | 13tok/sest. | 119 tok/s | chat, coding |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 44.7 GB | 128k | 11tok/sest. | 124 tok/s | chat |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 44.7 GB | 40k | 11tok/sest. | 124 tok/s | chat |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 44.7 GB | 40k | 11tok/sest. | 124 tok/s | chat |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 44.7 GB | 128k | 11tok/sest. | 123 tok/s | chat |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | fits | 157.7 GB | 1024k | 11tok/sest. | 26 tok/s | chat |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | fits | 166.5 GB | 1024k | 11tok/sest. | 26 tok/s | chat |
| MiniMax M3 MiniMax | UD-Q6_K | fits | 347.3 GB | 426k770k with q8 cache | 9tok/sest. | 64 tok/s | chat |
| granite 4.2 30b IBM | Q8_0 | fits | 62.3 GB | 128k | 8tok/sest. | 88 tok/s | chat |
| GLM 4.5V Z.ai | Q8_0 | fits | 130.2 GB | 64k | 8tok/sest. | 63 tok/s | chat |
| GLM 4.6V Z.ai | Q8_0 | fits | 130.2 GB | 128k | 8tok/sest. | 63 tok/s | chat |
| MiniMax M2 MiniMax | Q8_0 | fits | 258.8 GB | 192k | 7tok/sest. | 92 tok/s | chat |
| MiniMax M2.1 MiniMax | Q8_0 | fits | 258.8 GB | 192k | 7tok/sest. | 92 tok/s | chat |
| MiniMax M2.5 MiniMax | Q8_0 | fits | 258.8 GB | 192k | 7tok/sest. | 92 tok/s | chat |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q8_0 | fits | 111.2 GB | 128k | 5tok/sest. | 36 tok/s | – |
| GLM 4.7 Z.ai | Q6_K | fits | 321.5 GB | 198k | 4tok/sest. | 30 tok/s | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | fits | 169.1 GB | 256k | 3tok/sest. | 21 tok/s | – |
| Mistral Medium 3.5 128B Mistral AI | Q8_0 | fits | 169.1 GB | 256k | 3tok/sest. | 21 tok/s | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 386.6 GB | 92k160k with q8 cache | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 387.1 GB | 86k151k with q8 cache | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 386.6 GB | 92k160k with q8 cache | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 387.5 GB | 80k140k with q8 cache | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 387.5 GB | 80k140k with q8 cache | – | – | – |
| 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 | – | – | – | – |