Mac Studio M3 Ultra 512GB
£17,495
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 | £17,495 | eBay (used) | Buy |
| Total | £17,495 | |||
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 |
|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash DeepSeek | MXFP4 | fits | 148.8 GB | 1024k | 23tok/sest. | 84 tok/s | chat, coding |
| GLM 5.3 Flash Z.ai | Q8_0 | fits | 318.8 GB | 1024k | 12tok/sest. | 113 tok/s | – |
| Qwen 3.8 Flash Next Alibaba Qwen | Q8_0 | fits | 176.9 GB | 256k | 5tok/sest. | 88 tok/s | – |
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 30.0 GB | 256k | 17tok/sest. | 181 tok/s | chat |
| MiniMax M2.7 MiniMax | Q8_0 | fits | 235.0 GB | 200k | 16tok/sest. | 238 tok/s | chat |
| Qwen 3.5 122B-A10B Alibaba Qwen | Q8_0 | fits | 122.6 GB | 256k | 28tok/sest. | 424 tok/s | chat, coding |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 29.6 GB | 256k | 17tok/sest. | 181 tok/s | chat |
| gpt-oss 120B OpenAI | MXFP4 | fits | 61.0 GB | 128k | 74tok/sest. | 684 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder Next Alibaba Qwen | Q8_0 | fits | 80.6 GB | 256k | 64tok/sest. | 1021 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | Q8_0 | fits | 120.8 GB | 256k | 25tok/sest. | 428 tok/s | chat, coding, long documents |
| Gemma 4 31B | Q8_0 | fits | 34.5 GB | 256k | 15tok/sest. | 161 tok/s | chat |
| Mistral Small 4 119B Mistral AI | Q8_0 | fits | 119.3 GB | 1024k | 39tok/sest. | 471 tok/s | chat, coding |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.8 GB | 256k | 84tok/sest. | 1290 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 29.6 GB | 256k | 17tok/sest. | 181 tok/s | chat |
| Gemma 4 26B-A4B | Q8_0 | fits | 26.6 GB | 256k | 63tok/sest. | 1147 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q8_0 | fits | 115.9 GB | 128k | 13tok/sest. | 158 tok/s | chat |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.8 GB | 256k | 84tok/sest. | 1290 tok/s | chat, coding, agents, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q8_0 | fits | 80.6 GB | 256k | 80tok/sest. | 1215 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 32.1 GB | 198k | 45tok/sest. | 673 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 29.1 GB | 384k | 18tok/sest. | 191 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 33.6 GB | 256k | 89tok/sest. | 1472 tok/s | chat, coding, agents, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.8 GB | 128k | 99tok/sest. | 963 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q8_0 | fits | 49.7 GB | 1024k | 91tok/sest. | 1112 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 34.0 GB | 256k | 50tok/sest. | 593 tok/s | chat, coding, agents |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 41.2 GB | 40k | 12tok/sest. | 112 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 13.4 GB | 256k | 39tok/sest. | 419 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.7 GB | 256k | 50tok/sest. | 522 tok/s | chat, coding, long documents |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 29.1 GB | 128k | 18tok/sest. | 191 tok/s | chat |
| Gemma 3 27B | Q8_0 | fits | 30.4 GB | 128k | 17tok/sest. | 192 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 41.2 GB | 128k | 12tok/sest. | 129 tok/s | – |
| Llama 3.3 70B Meta | Q8_0 | fits | 80.6 GB | 128k | 6tok/sest. | 61 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 19.2 GB | 256k | 27tok/sest. | 290 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 20.4 GB | 40k | 25tok/sest. | 261 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 13.4 GB | 128k | 39tok/sest. | 430 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 13.4 GB | 40k | 39tok/sest. | 430 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q8_0 | fits | 21.5 GB | 16k | 24tok/sest. | 262 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 6.0 GB | 256k | 95tok/sest. | 977 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 13.4 GB | 256k | 39tok/sest. | 415 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 14.5 GB | 128k | 36tok/sest. | 396 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 9.3 GB | 128k | 58tok/sest. | 656 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 10.7 GB | 125k | 119tok/sest. | 2145 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 10.9 GB | 128k | 49tok/sest. | 454 tok/s | chat, coding |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.7 GB | 32k | 570tok/sest. | 4672 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 1.9 GB | 256k | 432tok/sest. | 4388 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.5 GB | 256k | 287tok/sest. | 2092 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 3.4 GB | 128k | 188tok/sest. | 1758 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 4.6 GB | 128k | 130tok/sest. | 1050 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 5.3 GB | 128k | 109tok/sest. | 1189 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 5.3 GB | 32k | 109tok/sest. | 1090 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 13.3 GB | 128k | 101tok/sest. | 1549 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 6.7 GB | 128k | 84tok/sest. | 762 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 6.9 GB | 128k | 81tok/sest. | 798 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 18.3 GB | 128k | 75tok/sest. | 1164 tok/s | chat, coding, agents, long documents |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 27.0 GB | 128k | 66tok/sest. | 1196 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 10.1 GB | 128k | 53tok/sest. | 514 tok/s | chat, coding |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 11.4 GB | 128k | 47tok/sest. | 358 tok/s | chat, coding |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 12.7 GB | 128k | 42tok/sest. | 454 tok/s | chat, coding |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 13.0 GB | 64k | 41tok/sest. | 358 tok/s | chat, coding |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 13.4 GB | 256k | 39tok/sest. | 415 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 21.4 GB | 128k | 24tok/sest. | 245 tok/s | chat, coding |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 29.1 GB | 128k | 18tok/sest. | 194 tok/s | chat |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 29.1 GB | 40k | 18tok/sest. | 194 tok/s | chat |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 29.1 GB | 40k | 18tok/sest. | 194 tok/s | chat |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 29.1 GB | 128k | 18tok/sest. | 191 tok/s | chat |
| MiniMax M2 MiniMax | Q8_0 | fits | 235.0 GB | 192k | 16tok/sest. | 238 tok/s | chat |
| MiniMax M2.1 MiniMax | Q8_0 | fits | 235.0 GB | 192k | 16tok/sest. | 238 tok/s | chat |
| MiniMax M2.5 MiniMax | Q8_0 | fits | 235.0 GB | 192k | 16tok/sest. | 238 tok/s | chat |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | fits | 149.1 GB | 1024k | 16tok/sest. | 70 tok/s | chat |
| GLM 4.5V Z.ai | Q8_0 | fits | 112.3 GB | 64k | 15tok/sest. | 171 tok/s | chat |
| GLM 4.6V Z.ai | Q8_0 | fits | 112.3 GB | 128k | 15tok/sest. | 171 tok/s | chat |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | fits | 157.9 GB | 1024k | 15tok/sest. | 70 tok/s | chat |
| MiniMax M3 MiniMax | UD-Q6_K | fits | 335.4 GB | 426k770k with q8 cache | 14tok/sest. | 143 tok/s | chat |
| granite 4.2 30b IBM | Q8_0 | fits | 37.8 GB | 128k | 13tok/sest. | 148 tok/s | chat |
| DeepSeek R1 DeepSeek | Q4_K_M | fits | 379.6 GB | 92k160k with q8 cache | 13tok/sest. | 65 tok/s | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | fits | 380.1 GB | 86k151k with q8 cache | 13tok/sest. | 65 tok/s | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | fits | 379.6 GB | 92k160k with q8 cache | 13tok/sest. | 65 tok/s | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | fits | 380.5 GB | 80k140k with q8 cache | 13tok/sest. | 65 tok/s | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | fits | 380.5 GB | 80k140k with q8 cache | 13tok/sest. | 64 tok/s | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q8_0 | fits | 80.6 GB | 128k | 6tok/sest. | 61 tok/s | – |
| GLM 4.7 Z.ai | Q8_0 | fits | 367.1 GB | 78k145k with q8 cache | 6tok/sest. | 74 tok/s | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | fits | 135.5 GB | 256k | 4tok/sest. | 35 tok/s | – |
| Mistral Medium 3.5 128B Mistral AI | Q8_0 | fits | 135.5 GB | 256k | 4tok/sest. | 34 tok/s | – |
| 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 | – | – | – | – |