OpenWeightsTerminal

Qwen3.8-27B

Qwen3.8-27B

DGX Spark · 4-bit · TensorFold

Decode · tok/s
102.9
Prefill
—
tok/100W
42.9
Qwen3.8-27B just hit 102.9 tok/s on a single DGX Spark with TensorFold.

Rank is the quoted 102.9.

Officialclaimed
Open pair