OpenWeightsTerminal

Qwen3.8-Flash-Next

Qwen3.8-Flash-Next

DGX Spark · NVFP4 · TensorFold

Decode · tok/s
74.8
Prefill
—
tok/100W
31.2
Qwen3.8-Flash-Next (NVFP4, MTP-6). Fixed 2,048-token code task: 74.8 tok/s single-stream decode

Rank is the quoted 74.8 single-stream. Context sweep 56–65 skipped as a range. 50.8 at 260k stays in the note.

Officialclaimed
Open pair