Alibaba releases Qwen3.8-Flash-Next, previewing Qwen4 architecture
Qwen3.8-Flash-Next is a multimodal MoE with 125B parameters plus 51B N-gram embeddings, activating only 6B per token. It beats Claude Opus 4.6 Max on 8 of 9 comparable benchmarks. Native 262K context, extensible to 1M with YaRN; QwenCloud API pricing at $0.16/1M input and $0.47/1M output tokens.
How this story unfolded
6 days · 14 reports · 38 community posts · 52 of 55 shown
- Aug 25
- Aug 26
Alibaba’s Qwen to open-source Qwen3.8-Flash-Next, previewing Qwen4 architecturetechnode.com
unsloth/Qwen3.8-Flash-Next-GGUFhuggingface.co
Alibaba’s Qwen Team Releases Qwen3.8-Flash-Next: A 125B Multimodal MoE With 6B Active Parameters Previewing the Qwen4 Architecturemarktechpost.com
Experiment with Qwen3.8-Flash-Next 176B Model on NVIDIA GB300 NVL72 for Agentic Codingdeveloper.nvidia.com
- Aug 27
- Aug 28
- Aug 29
- Aug 30
- Aug 31
Qwen by email
Get an email when Qwen has news
No news that day, no email.
More stories today
- Open-source RL training with trl and OpenEnv shared
- NVIDIA invests $3.5B in MediaTek, deepens AI partnership
- Neta team explains why their open-source model generated Anne Hathaway-like images
- OpenAI age-verification error deletes adult's account
- South Korea gives citizens free unlimited domestic AI access