Can DeepSeek V4 Flash run on the DGX Spark?
Yes. At 8K context the best fit is Q2_K, using about 103 GB of the 109 GB usable on the DGX Spark. Estimated speed ceiling: ~52 tokens/sec.
Newer compressed-attention design: long-context figures are an upper bound.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | 103 GB Tight | 103 GB Tight | 105 GB Tight | 114 GB No | 52 |
| 3-bit (Q3_K_M) | 133 GB No | 134 GB No | 136 GB No | 145 GB No | — |
| 4-bit (Q4_K_M) | 167 GB No | 167 GB No | 169 GB No | 178 GB No | — |
| 5-bit (Q5_K_M) | 194 GB No | 194 GB No | 197 GB No | 206 GB No | — |
| 6-bit (Q6_K) | 223 GB No | 224 GB No | 226 GB No | 235 GB No | — |
| 8-bit (Q8_0) | 289 GB No | 289 GB No | 292 GB No | 301 GB No | — |
| 16-bit (F16/BF16) | 543 GB No | 543 GB No | 546 GB No | 555 GB No | — |
• real GGUF file size. Speed is a bandwidth ceiling (273 GB/s), not a benchmark. Methodology.
More
DeepSeek V4 Flash on every GPU and Mac · Every model that runs on the DGX Spark · Other models that fit 64 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (deepseek-ai/DeepSeek-V4-Flash), NVIDIA specs. Data as of 2026-11-17.