DiggTop

DGX Spark vs RTX 3080

Best verified output tok/s per model (single-stream generation). Hover a value for the quant.

DGX Spark44 verified runs · best 86.8 tok/s
RTX 30809 verified runs · best 277.8 tok/s
ModelDGX SparkRTX 3080
LFM2.5-8B-A1B277.8 Q6_K
Qwen 3.8 Flash86.8 EXL3 3.05bpw
Ornith-1.5-9B82.8 Q6_K
Qwen3.8-27B-Uncensored74.1 IQ2_XXS
Bonsai-27B72.9 Q1_0
Qwen3.8-Flash-Next72.0 EXL3
gemma-4-12B-it-qat71.2 Q4_0
Ornith-1.5-35B-A3B64.4 Q4_K_M
GLM-5.3-Flash64.1 EXL3 2.05 bpw
Qwen3.8-Flash-Next-hibrid4860.0 NVFP4 (output head)
gpt-oss-20b57.1 MXFP4
Qwen3.8-27B56.0 NVFP4 W4A444.4 IQ2_XXS
DeepSeek-V4.1-Flash47.0 FP4
Muse-Glimmer-30B6.0 Q4_K_M

Head-to-head (models tested on both): DGX Spark 1 · RTX 3080 0 · tied 0 · data as of Sep 23, 2026. Full rules: methodology.

Related reading: RTX 5090 vs 3090 · quantization · Value index · Full board