#qwen

[推广] Qwen Image 2.1 Pro 与 Nano Banana 2.1：透明编辑、视频参考和多轮修图怎么选？

Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s

I made my iPhone a second GPU for my MacBook-Qwen 3.8 27B prefills 29–44% faster

离谱！OpenAI智能体攻击Hugging Face时，竟想叫DeepSeek、Kimi和Qwen来帮忙

leejet/stable-diffusion.cpp

Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

Kev: Tiny Jev-like family of decision models built on top of Qwen3.5

Qwen Image 2.1

Shapelearn Qwen 3.8 27B (13.1 GB VRAM)

Qwen 3.8 Omni Flash

Run QWEN3.8 27B on 16gb Nvidia GPUs

Show HN: Swift-Qwen3.8-27B, -58.3% thinking, x1.95 speed, accuracy of xhigh

Show HN: Nari Qwen3-TTS and Qwen3-ASR – High accuracy, low latency and cost

这个本地模型，让我 token 自由了

Qwen3.8-27B 把旗舰级 Agent 能力搬进个人电脑，本地运行不花 API 费用，但速度、内存和长任务体验仍有明显门槛。