AISimon Willisonabout 2 hours ago
Qwen3.8-Flash-Next
1 min read
Qwen released Qwen3.8-Flash-Next, a multimodal MoE model with 125B total tokens and 6B active, serving as an early preview of Qwen4's architecture. Simon Willison tested Unsloth quantized versions on a DGX Spark, including the 72.5GB UD-IQ1_S and 78.9GB UD-Q2_K_XL.
Level
Hype check
Tap to vote and see what everyone thinks.
Summary by ByteBrief
