Research2h ago
Research
Qwen Releases Flash-Next Architecture Preview
The Qwen3.8-Flash-Next model utilizes a Mixture-of-Experts architecture with 125B total parameters but only 6B active. This configuration serves as an early preview for the upcoming Qwen4 series. Early tests using Unsloth quantized versions show high reasoning capabilities. Practitioners can now evaluate this specific MoE efficiency before the full next-generation release.