Alibaba Qwen Releases Qwen3.8-Flash, a 125B Multimodal MoE Previewing Qwen4
Sign in✓ Signed in
Alibaba’s Qwen team on Wednesday released Qwen3.8-Flash, a multimodal mixture-of-experts model, and opened the weights of Qwen3.8-Flash-Next as an early preview of the architecture planned for Qwen4. The open checkpoint pairs a 125-billion-parameter main network with 51 billion n-gram embedding parameters, activating 6 billion parameters per token, and supports 262,144 tokens of native context, extensible to 1 million tokens with YaRN.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...