Qwen3 · Issues· 68 open

Verify evals on Papers with Code

[Bug] Qwen3.8-Max: web_search tool fails during long sessions, model hallucinates URLs on chat.qwen.ai

China Turkey open benchmark for clinical AI safety

Qwen3.8 chat template crashes on OpenAI JSON-string tool arguments

[论文分享] LUMEN：用电子能量"旋钮"制造自然界没有的光 —— 13.5nm EUV 光源的闭式全量验证（附 2 篇论文 PDF）

Independent from-scratch Qwen-14B step reimplementation (no PyTorch, no cuBLAS, own compiler) — what matched, what it cost, and a LoRA-shape finding

Qwen3-4B enters a repetitive reasoning loop on a trivial arithmetic task

Tool-call emission loses its prefix — only the tail of the argument JSON arrives (qwen3.8-max-preview)

Qwen3 tool-use: relative file paths in Write/Edit resolve to /tmp instead of the system-prompt working directory

[Badcase]: Qwen-Chat 3: Polish grammar errors & garbled Polish text on images

[APEX研究] 商业模式 通义千问 Qwen3 定价策略与商业化路径

[APEX研究] ⚙️ 技术架构 通义千问 Qwen3 跨模型技术架构深度对比分析

[APEX研究] 生态系统 通义千问 Qwen3 开源战略与开发者生态构建

Question: Claims about Qwen3.5 beating US models on speed/cost and cross-app agent capabilities

Chat template breaks KV-cache reuse when enable_thinking=false