Skip to content
Qwen 3.8 flash next

Qwen 3.8 flash next

Running the Qwen3.8-Flash-Next model

On discrete GPU with a large system RAM

  • Basalt : Local inference engine for Qwen3.8-Flash-Next on NVIDIA Blackwell.
  • PolyStrata : supports various MoE models.
  • Strata : runs Qwen3.8-Flash-Next and DeepSeekV4.1-Flash-1017 from 12GB+ VRAM with smart expert caching.

On one DGX spark

Others

Last updated on