Qwen3.8-Flash-Next
Alibaba (Qwen)vllm serve Qwen/Qwen3.8-Flash-Next --port 8000 --tensor-parallel-size 4
1 more from this model
vllm serve Qwen/Qwen3.8-Flash-Next-FP8 \ --tensor-parallel-size 4
general family · filed under inference & serving
Partitions model computation across GPUs; the cited serving configurations specify particular parallelism degrees.
The sources on this page name it without explaining how it works. The line above is the extraction's one-line gloss. See serving parallelism for the methods filed beside it.
Also called Four-way tensor parallelism for serving, tensor-parallel-size 4, tensor-parallel serving on 8 GPUs, tensor parallel on 8 GPUs, Tensor parallelism with degree four, TP4.
4 quotes from 4 sources, one card per model, each opening with its strongest.
vllm serve Qwen/Qwen3.8-Flash-Next --port 8000 --tensor-parallel-size 4
vllm serve Qwen/Qwen3.8-Flash-Next-FP8 \ --tensor-parallel-size 4
--tensor-parallel-size 8
using tensor parallel on 8 GPUs