DGX Spark 128GB
$8,650
Parts
A complete machine needs no part checks.
| Component | Selection | Price | Where | Buy |
|---|---|---|---|---|
| Machine | NVIDIA DGX Spark 128GB 128 GB unified · 273 GB/s | $8,650 | eBay | Buy |
| Total | $8,650 | |||
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 |
|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | fits | 91.6 GB | 312k557k with q8 cache | 14tok/sest. | 437 tok/s | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | fits | 102.2 GB | 1018k1024k with q8 cache | 12tok/sest. | 444 tok/s | – |
| Qwen 3.8 Flash Next Alibaba Qwen | Q4_K_M | fits | 112.4 GB | 232k256k with q8 cache | 3tok/sest. | 224 tok/s | – |
| MiniMax M2.7 MiniMax | UD-Q3_K_M | fits | 97.0 GB | 96k178k with q8 cache | 15tok/sest. | 986 tok/s | – |
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 28.4 GB | 256k | 6tok/sest. | 488 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | Q6_K | fits | 95.1 GB | 256k | 12tok/sest. | 1291 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 28.0 GB | 256k | 6tok/sest. | 488 tok/s | – |
| gpt-oss 120B OpenAI | MXFP4 | fits | 60.1 GB | 128k | 30tok/sest. | 2189 tok/s | chat, coding |
| Qwen3 Coder Next Alibaba Qwen | Q8_0 | fits | 80.0 GB | 256k | 23tok/sest. | 3261 tok/s | chat, coding |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q6_K | fits | 107.8 GB | 256k | 9tok/sest. | 1137 tok/s | – |
| Gemma 4 31B | Q8_0 | fits | 32.5 GB | 256k | 5tok/sest. | 426 tok/s | – |
| Mistral Small 4 119B Mistral AI | Q8_0 | fits | 118.7 GB | 18k29k with q8 cache | 13tok/sest. | 1687 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.3 GB | 256k | 31tok/sest. | 4182 tok/s | chat, coding, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 28.0 GB | 256k | 6tok/sest. | 488 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 26.1 GB | 256k | 22tok/sest. | 3187 tok/s | chat, coding |
| GLM 4.5 Air Z.ai | Q8_0 | fits | 111.6 GB | 48k87k with q8 cache | 5tok/sest. | 644 tok/s | – |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.3 GB | 256k | 31tok/sest. | 4182 tok/s | chat, coding, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q8_0 | fits | 80.0 GB | 256k | 30tok/sest. | 4100 tok/s | chat, coding, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 30.8 GB | 198k | 18tok/sest. | 2341 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 25.3 GB | 384k | 6tok/sest. | 550 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 33.4 GB | 256k | 30tok/sest. | 4358 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.2 GB | 128k | 39tok/sest. | 3027 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q8_0 | fits | 49.5 GB | 1024k | 31tok/sest. | 3975 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 31.7 GB | 256k | 25tok/sest. | 3026 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 35.2 GB | 40k | 5tok/sest. | 376 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 13.0 GB | 256k | 13tok/sest. | 1110 tok/s | – |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 9.9 GB | 256k | 17tok/sest. | 1406 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 25.3 GB | 128k | 6tok/sest. | 550 tok/s | – |
| Gemma 3 27B | Q8_0 | fits | 28.5 GB | 128k | 6tok/sest. | 495 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 35.2 GB | 128k | 5tok/sest. | 394 tok/s | – |
| Llama 3.3 70B Meta | Q8_0 | fits | 73.1 GB | 128k | 2tok/sest. | 184 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 15.4 GB | 256k | 11tok/sest. | 913 tok/s | – |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 16.6 GB | 40k | 10tok/sest. | 848 tok/s | – |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 10.0 GB | 128k | 17tok/sest. | 1484 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 10.0 GB | 40k | 17tok/sest. | 1484 tok/s | chat |
| Phi-4 14B Microsoft | Q8_0 | fits | 16.8 GB | 16k | 10tok/sest. | 854 tok/s | – |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.2 GB | 256k | 35tok/sest. | 2831 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.2 GB | 256k | 17tok/sest. | 1387 tok/s | chat |
| Granite 4.2 8B IBM | Q8_0 | fits | 10.7 GB | 128k | 16tok/sest. | 1377 tok/s | chat |
| Gemma 4 E4B | Q8_0 | fits | 8.6 GB | 128k | 20tok/sest. | 1704 tok/s | chat |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.5 GB | 125k | 69tok/sest. | 9945 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q6_K | fits | 7.9 GB | 128k | 22tok/sest. | 1532 tok/s | chat |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.3 GB | 32k | 268tok/sest. | 20815 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 1.6 GB | 256k | 182tok/sest. | 14321 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.2 GB | 256k | 109tok/sest. | 5874 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 2.7 GB | 128k | 80tok/sest. | 6551 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 3.6 GB | 128k | 56tok/sest. | 4330 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 3.9 GB | 128k | 50tok/sest. | 4359 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 3.9 GB | 32k | 50tok/sest. | 3846 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 4.7 GB | 128k | 39tok/sest. | 2885 tok/s | chat, coding |
| granite 4.2 3b IBM | Q8_0 | fits | 5.0 GB | 128k | 37tok/sest. | 3101 tok/s | chat, coding |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 25.1 GB | 128k | 36tok/sest. | 5223 tok/s | chat, coding |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 12.9 GB | 128k | 36tok/sest. | 4792 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 17.6 GB | 128k | 29tok/sest. | 4040 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 8.7 GB | 128k | 20tok/sest. | 1653 tok/s | chat |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 9.7 GB | 128k | 18tok/sest. | 1532 tok/s | chat |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 10.2 GB | 256k | 17tok/sest. | 1387 tok/s | chat |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 10.4 GB | 128k | 16tok/sest. | 1199 tok/s | chat |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 12.0 GB | 64k | 14tok/sest. | 1199 tok/s | – |
| MiniMax M2.5 MiniMax | MXFP4 | fits | 118.0 GB | 12k22k with q8 cache | 13tok/sest. | 985 tok/s | – |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 16.9 GB | 128k | 10tok/sest. | 831 tok/s | – |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 25.3 GB | 128k | 6tok/sest. | 560 tok/s | – |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 25.3 GB | 40k | 6tok/sest. | 560 tok/s | – |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 25.3 GB | 40k | 6tok/sest. | 560 tok/s | – |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 25.3 GB | 128k | 6tok/sest. | 550 tok/s | – |
| GLM 4.5V Z.ai | Q8_0 | fits | 108.0 GB | 64k | 6tok/sest. | 738 tok/s | – |
| GLM 4.6V Z.ai | Q8_0 | fits | 108.0 GB | 67k123k with q8 cache | 6tok/sest. | 738 tok/s | – |
| granite 4.2 30b IBM | Q8_0 | fits | 31.7 GB | 128k | 5tok/sest. | 444 tok/s | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q8_0 | fits | 73.1 GB | 128k | 2tok/sest. | 184 tok/s | – |
| Mistral Medium 3.5 128B Mistral AI | Q6_K | fits | 99.0 GB | 65k120k with q8 cache | 2tok/sest. | 102 tok/s | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 377.9 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 378.4 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 377.9 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 378.8 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 378.8 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 147.1 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 155.8 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | won't run | 127.2 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 205.2 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 421.4 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 435.3 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 747.8 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 579.4 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 579.9 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 579.9 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 579.9 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 131.5 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 131.5 GB | – | – | – | – |
| MiniMax M3 MiniMax | UD-Q4_K_M | won't run | 248.4 GB | – | – | – | – |