Alibaba Qwen team open-sources Qwen3.8-Flash-Next weights (125B total / 6B active MoE). Partnering with Unsloth, optimized GGUF quantizations run full 262K context on single 24GB GPUs at 85 tokens/sec.
Alibaba Qwen confirmed that the 125B multimodal MoE Qwen3.8-Flash-Next can now run locally on about 75GB of RAM via Unsloth GGUFs, with N-gram embeddings offloaded to CPU or unified memory for near-VRAM speed. It is the day-0 local path for the Qwen4 architecture preview weights.
Cline announced that GLM-5.3 Flash, previously previewed as Ox Alpha, is free in Cline. The 320B-parameter mixture-of-experts model with 18B active parameters is beating frontier models on benchmarks and has become Cline fastest-growing model, driving over 11% of all traffic in less than a week.
Alibaba Qwen announced that the production Qwen3.8-Flash API is live on QwenCloud at $0.16 input and $0.47 output per 1M tokens. The multimodal MoE activates only 6B parameters per token and is positioned as cheaper and stronger than Qwen3.7-Plus on coding and office workloads.