Qwen3.8 Flash Next has no model page of its own yet — this page exists so its self-hosted GPU benchmark results have somewhere to live. See how it scores against every other model on Vision Evals.
One quantization of Qwen3.8 Flash Next, served with vLLM from the published weights and scored on the same tasks as the hosted models. Expand a row for the GPUs it was measured on.
| Quantization | Weights | Overall score | Detection mAP50 | Single-stream tok/s |
|---|---|---|---|---|
| 172.8 GB | 55.3% | 54.3% | – |
Rows are ordered by overall score. Every score is the mean of three runs per task under the benchmark protocol (a row marked single run has one), and the gap between quantizations is usually inside the run-to-run range, so read the order as a guide rather than a verdict. Self-hosted rows run with thinking on, the same setting as the hosted frontier models; some hosted open-weight rows still run without thinking, so a self-hosted quant can score above its own hosted API. Quantization still costs a little precision.