Released on Aug 14, 2026
Il modello dense multimodale della generazione Qwen3.8 di Alibaba: 27,78B di parametri, input testo+immagini+video e contesto nativo di 262K token. Licenza Apache 2.0. L'attenzione ibrida (DeltaNet lineare + GQA) riduce la KV cache di circa il 75% rispetto a un transformer standard: in Q4_K_M sta su una singola GPU da 24GB.
Generazione Qwen3.8: dense 27,78B nativamente multimodale (testo, immagini, video), contesto 262K, Apache 2.0. Attenzione ibrida 48× Gated DeltaNet + 16× GQA con KV cache ridotta del 75% e MTP integrato nel checkpoint.
Visit the official site to download, learn more and start using Qwen3.8-27B.
7B open-weight model (32-layer DiT) that unifies text-to-image generation up to 2048x2048, editing with up to 10 reference images, and native RGBA transparency. Designed to run locally on 16GB+ VRAM; supported by diffusers and ComfyUI.
Ultra-compact 0.5B-parameter model. Runs on any hardware, even embedded: ideal for lightweight summarization and low-power local devices.
Clear step up in reasoning and instruction quality over 8B models. Excellent for coding, agents and structured writing on 16GB GPUs or Macs with 32GB RAM.
