Can ERNIE 5.5 Flash Base run on the DGX Spark?
Yes. At 8K context the best fit is Q2_K, using about 101 GB of the 109 GB usable on the DGX Spark.
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) | 101 GB Tight | 101 GB Tight | 103 GB Tight | 108 GB Tight | — |
| 3-bit (Q3_K_M) | 131 GB No | 132 GB No | 133 GB No | 138 GB No | — |
| 4-bit (Q4_K_M) | 164 GB No | 164 GB No | 166 GB No | 171 GB No | — |
| 5-bit (Q5_K_M) | 191 GB No | 191 GB No | 193 GB No | 198 GB No | — |
| 6-bit (Q6_K) | 220 GB No | 220 GB No | 221 GB No | 227 GB No | — |
| 8-bit (Q8_0) | 284 GB No | 284 GB No | 286 GB No | 291 GB No | — |
| 16-bit (F16/BF16) | 534 GB No | 534 GB No | 536 GB No | 541 GB No | — |
• real GGUF file size. Speed is a bandwidth ceiling (273 GB/s), not a benchmark. Methodology.
More
ERNIE 5.5 Flash Base 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 (baidu/ERNIE-5.5-Flash-Base), NVIDIA specs. Data as of 2026-11-17.