Qwen3.5-0.8B 发布 LiteRT-LM 端侧量化版本
原标题：litert-community/Qwen3.5-0.8B
AI 摘要
Hugging Face 上发布了 litert-community/Qwen3.5-0.8B，这是将阿里 Qwen3.5-0.8B 混合架构模型转换为 Google LiteRT-LM 格式的端侧推理包，提供 int8 量化及文本、视觉多个版本。该包据称是首个 LiteRT 形式的 Qwen3.5，也是首个由已发布 LiteRT-LM 运行时支持的 gated-delta-net 混合模型，并已在 Galaxy S26、iPhone 17 Pro、Mac Studio M4 Max 上实测解码与预填充速度。
正文节选
--- license: apache-2.0 base_model: Qwen/Qwen3.5-0.8B tags: - litert - litert-lm - litertlm - on-device - edge - hybrid - gated-deltanet - qwen3_5 pipeline_tag: text-generation library_name: litert-lm base_model_relation: quantized --- LiteRT is Google's on-device runtime, the new name for TensorFlow Lite (Android: `com.google.ai.edge.litert:litert`), and `litert-torch`, the renamed `ai-edge-torch`, is its PyTorch converter: a PyTorch model converted unmodified with `litert_torc