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 128k context. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @128k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | fits | 102.4 GB | 312k557k with q8 cache | 6tok/sest. | 68 tok/s | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | fits | 104.2 GB | 1018k1024k with q8 cache | 10tok/sest. | 114 tok/s | – |
| Qwen 3.8 Flash Next Alibaba Qwen | Q4_K_M | fits | 115.9 GB | 232k256k with q8 cache | 2tok/sest. | 196 tok/s | – |
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 36.6 GB | 256k | 5tok/sest. | 343 tok/s | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | fits | 102.6 GB | 194k200k with q8 cache | 3tok/sest. | 229 tok/s | chat |
| Qwen 3.5 122B-A10B Alibaba Qwen | Q6_K | fits | 98.7 GB | 256k | 9tok/sest. | 610 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 36.2 GB | 256k | 5tok/sest. | 343 tok/s | – |
| Qwen3 Coder Next Alibaba Qwen | Q8_0 | fits | 83.5 GB | 256k | 14tok/sest. | 1352 tok/s | chat, coding |
| gpt-oss 120B OpenAI | MXFP4 | fits | 65.0 GB | 128k | 13tok/sest. | 904 tok/s | chat, coding |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q6_K | fits | 109.5 GB | 256k | 8tok/sest. | 856 tok/s | – |
| Gemma 4 31B | Q8_0 | fits | 42.6 GB | 256k | 4tok/sest. | 326 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q6_K | fits | 96.9 GB | 923k1024k with q8 cache | 11tok/sest. | 529 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 38.4 GB | 256k | 17tok/sest. | 1667 tok/s | chat, coding, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 36.2 GB | 256k | 5tok/sest. | 343 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 29.2 GB | 256k | 14tok/sest. | 2024 tok/s | chat, coding |
| GLM 4.5 Air Z.ai | Q6_K | fits | 116.7 GB | 128k | 3tok/sest. | 153 tok/s | – |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 38.4 GB | 256k | 17tok/sest. | 1667 tok/s | chat, coding, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q8_0 | fits | 83.5 GB | 256k | 16tok/sest. | 1477 tok/s | chat, coding, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 37.7 GB | 198k | 8tok/sest. | 786 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 44.8 GB | 384k | 4tok/sest. | 307 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 34.8 GB | 256k | 24tok/sest. | 2242 tok/s | chat, coding, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q8_0 | fits | 51.1 GB | 1024k | 24tok/sest. | 1251 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 15.7 GB | 128k | 18tok/sest. | 1310 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 43.7 GB | 256k | 6tok/sest. | 485 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 65.9 GB | 40k | 2tok/sest. | 138 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 15.6 GB | 256k | 11tok/sest. | 841 tok/s | – |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 14.4 GB | 256k | 12tok/sest. | 1000 tok/s | chat |
| Gemma 3 27B | Q8_0 | fits | 38.6 GB | 128k | 4tok/sest. | 420 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 44.8 GB | 128k | 4tok/sest. | 307 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 65.9 GB | 128k | 2tok/sest. | 184 tok/s | – |
| Llama 3.3 70B Meta | Q8_0 | fits | 111.3 GB | 128k | 1tok/sest. | 89 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 34.8 GB | 256k | 5tok/sest. | 394 tok/s | – |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 36.1 GB | 40k | 5tok/sest. | 335 tok/s | – |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 27.6 GB | 128k | 6tok/sest. | 507 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 27.6 GB | 40k | 6tok/sest. | 507 tok/s | chat |
| Phi-4 14B Microsoft | Q8_0 | fits | 41.0 GB | 16k | 4tok/sest. | 336 tok/s | – |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 9.7 GB | 256k | 19tok/sest. | 1558 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 26.9 GB | 256k | 6tok/sest. | 513 tok/s | chat |
| Granite 4.2 8B IBM | Q8_0 | fits | 30.2 GB | 128k | 6tok/sest. | 461 tok/s | chat |
| Gemma 4 E4B | Q8_0 | fits | 12.6 GB | 128k | 14tok/sest. | 1402 tok/s | chat |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 15.8 GB | 125k | 14tok/sest. | 1874 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q6_K | fits | 23.6 GB | 128k | 7tok/sest. | 553 tok/s | chat |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 3.4 GB | 32k | 79tok/sest. | 4211 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 3.7 GB | 256k | 69tok/sest. | 5616 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 4.3 GB | 256k | 55tok/sest. | 3591 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 6.7 GB | 128k | 30tok/sest. | 1882 tok/s | chat, coding, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 15.3 GB | 128k | 22tok/sest. | 2168 tok/s | chat, coding, agents, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 9.2 GB | 128k | 20tok/sest. | 1012 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 11.6 GB | 128k | 16tok/sest. | 1298 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 11.6 GB | 32k | 16tok/sest. | 1248 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 21.8 GB | 128k | 14tok/sest. | 1361 tok/s | chat, coding |
| granite vision 4.1 4b IBM | Q8_0 | fits | 14.8 GB | 128k | 12tok/sest. | 801 tok/s | chat, coding |
| granite 4.2 3b IBM | Q8_0 | fits | 15.1 GB | 128k | 12tok/sest. | 817 tok/s | chat, coding |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 15.8 GB | 128k | 11tok/sest. | 439 tok/s | chat |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 16.0 GB | 128k | 11tok/sest. | 672 tok/s | chat |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 17.4 GB | 64k | 10tok/sest. | 439 tok/s | – |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 35.2 GB | 128k | 8tok/sest. | 1095 tok/s | chat, coding |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 25.4 GB | 128k | 7tok/sest. | 553 tok/s | chat |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 26.9 GB | 256k | 6tok/sest. | 513 tok/s | chat |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 40.1 GB | 128k | 4tok/sest. | 297 tok/s | – |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 44.8 GB | 128k | 4tok/sest. | 310 tok/s | – |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 44.8 GB | 40k | 4tok/sest. | 310 tok/s | – |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 44.8 GB | 40k | 4tok/sest. | 310 tok/s | – |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 44.8 GB | 128k | 4tok/sest. | 307 tok/s | – |
| GLM 4.5V Z.ai | Q4_K_M | fits | 83.7 GB | 64k | 3tok/sest. | 158 tok/s | – |
| GLM 4.6V Z.ai | Q4_K_M | fits | 90.1 GB | 128k | 3tok/sest. | 158 tok/s | – |
| granite 4.2 30b IBM | Q8_0 | fits | 62.4 GB | 128k | 3tok/sest. | 219 tok/s | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q8_0 | fits | 111.3 GB | 128k | 1tok/sest. | 89 tok/s | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | fits | 115.2 GB | 138k256k with q8 cache | 1tok/sest. | 52 tok/s | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 386.7 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 387.2 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 386.7 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 387.6 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 387.6 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 157.8 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 166.6 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | won't run | 169.2 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 249.0 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 432.4 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 446.3 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 758.7 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 588.2 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 588.6 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 588.6 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 588.6 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 161.3 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 161.3 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 147.7 GB | 12k22k with q8 cache | – | – | – |
| MiniMax M3 MiniMax | UD-Q4_K_M | won't run | 263.2 GB | – | – | – | – |