| Update README.md | Pq234 | open | 0 | disc |
| IDEA: Bitnet 1.58 (a4.8) version in future variants would be so incredible! | apiarium | open | 0 | disc |
| Interesting work — mobile AI perspective | 3morixd | open | 0 | disc |
| Listed on OpenModelMap | duola15 | open | 0 | disc |
| Qwen3.7-31B-it ? | kenleo | open | 0 | disc |
| What kind of effect if I increase the expert number used in lm studio? | boldos | open | 0 | disc |
| Regarding Qwen 3.6 35B-A3B reasoning/thinking mode | bardenthenry | open | 0 | disc |
| Add EvalEval community eval results | EvalEvalBot | closed | 0 | disc |
| Why return empty messages? | xingmo | closed | 0 | disc |
| Why is the intermediate dimension in the MoE experts *smaller* than the hidden dimension? | encryptedoreo | open | 0 | disc |
| Possible issue: completion-only output may contain </think> without a preceding <think> due to chat template prefill | molujia | open | 0 | disc |
| Update README.md | aathi1324 | closed | 0 | disc |
| Qwen3.6 support for TRT-LLM? | thecomputerguy81 | open | 0 | disc |
| Add MMMU-Pro evaluation result | SaylorTwift | open | 0 | disc |
| Running Qwen 3.6 35B-A3B on a single 8GB consumer laptop GPU (RTX 4060) | myeongjun77 | open | 0 | disc |
| Request versions in other sizes. | jian2023 | open | 0 | disc |
| 100b version | TheBigBlockPC | open | 0 | disc |
| Wrong tag qwen3_5_moe , unless you guys use some architecture change as the tag ,idk | Kz000000 | open | 0 | disc |
| how to enable non-thinking mode of this model in llama.cpp? | daijava | open | 0 | disc |
| Create Alpha and Omega 1.01 | Kjppmp | open | 0 | disc |
| 照顾一下Tesla T4的老人，需要8B、9B、14B、16B参数 | zhousp666 | open | 0 | disc |
| Tool use failure [Fix Found] | JonnyWhatshisface | open | 0 | disc |
| Is it really better in real world task? | BornSaint | open | 0 | disc |
| Built a multimodal open source app on Qwen3.6-35B-A3B: vision reasoning, doc-to-JSON, screenshot-to-React, runs on Ollama or llama.cpp | gvij | open | 0 | disc |
| Request: DOI | dancinlife | open | 0 | disc |
| Qwen3.6_9-12B_A2B_MoE | Konti201203 | open | 0 | disc |
| Qwen3.6 200B? | celikburak | open | 0 | disc |
| Upload IMG-20260421-WA0030.jpg | jannybaby99 | open | 0 | disc |
| Upload IMG-20260421-WA0030.jpg | jannybaby99 | open | 0 | disc |
| Upload IMG-20260421-WA0030.jpg | jannybaby99 | open | 0 | disc |
| My Mac mini 16GB would like to formally request Qwen3.6-9B 🤣 | OliverTD | open | 0 | disc |
| Cambia el idioma a español | kenedy698 | open | 0 | disc |
| Very buggy in vllm + opencode | void009 | open | 0 | disc |
| 1 тема | Yackiv | open | 0 | disc |
| Long video - crash | Marbuel | open | 0 | disc |
| My RTX 3090 ran out of excuses: Qwen3.6-35B-A3B | Kukedlc | open | 0 | disc |
| Image - resolution - tokens | Marbuel | open | 0 | disc |
| Question about UI navigation and coordinates | ztsvvstz | open | 0 | disc |
| GPTQ Int4 Quant | nikhilr12 | open | 0 | disc |
| Add LICENSE file | deepsweet | open | 0 | disc |
| Qwen3.6 | willowoods | draft | 0 | disc |
| a3b jinja template (165898 token session) no errors, opencode | KuziaMother | open | 0 | disc |
| tool calling failed with claude code | weisunding | open | 0 | disc |
| Something happened. | owao | open | 0 | disc |
| ES QWEN LA MEJOR EMPRESA DE INTELIGENCIA ARTIFICIAL DEL MUNDO ENTERO | josenoya | open | 0 | disc |
| P=nP | Nearbe | open | 0 | disc |
| Add ParseBench evaluation results | boyang-runllama | open | 0 | disc |
| 123 | Kfans | draft | 0 | disc |
| Question from a nOOb. | m3thod | open | 0 | disc |
| Inconsistent parameters recommendation | PhilippeEiffel | open | 0 | disc |
| Excellent SVG improve since last version! | kq | open | 0 | disc |
| 太吃显存啦 | yukojiangjiang | open | 0 | disc |
| Poor tools use and endless resoning loop | qiaozhiyi | open | 0 | disc |
| endless reasoning loops | phoebdroid | open | 0 | disc |
| Smaller models, embedding and reranker models | Duonglv | open | 0 | disc |
| Your model is excellent, thank you very much! Waiting for the 122b model, version 3.6! But... | Kosh69 | open | 0 | disc |
| Add ParseBench evaluation results | boyang-runllama | closed | 0 | disc |
| Installation Video and Testing - Step by Step | fahdmirzac | open | 0 | disc |
| Incredible! Qwen 3.6 is simply unbelievable! | Mithnick | open | 0 | disc |
| Architectural Comparison: Qwen3.5-35B-A3B vs. Qwen3.6-35B-A3B | BuiDoan | open | 0 | disc |
| [GUIDE] Run Qwen3.6-35B-A3B at full context on a 4090 and GB10 Spark with vLLM and Llama.cpp | erdal | open | 0 | disc |
| A Quick Note of Thanks to the Qwen Team 🙏 | nikhilprasanth | open | 0 | disc |
| Qwen/Qwen3.6-35B-A3B-GPTQ-Int4? | sujithr | open | 0 | disc |
| Thanks for contributing to the OpenWeight Community | Manuun1 | open | 0 | disc |
| Where's 397b? | ebfio | open | 0 | disc |
| Any new QwenGuard ? | mostafa-amer2 | open | 0 | disc |
| Prescence penalty 1.5 | Sliderpro93 | open | 0 | disc |
| Many thanks! | maglat | open | 0 | disc |
| Add community evaluation results for AIME_2026, GPQA, HLE, HMMT_FEB_2026, MMLU-PRO, SWE-BENCH_PRO, SWE-BENCH_VERIFIED, TERMINAL-BENCH-2.0 | nielsr | open | 0 | disc |
| Qwen3.6-27B? | lingyezhixing | open | 0 | disc |
| 祝贺!!! | cai2023 | open | 0 | disc |