| Listed on OpenModelMap | duola15 | open | 0 | disc |
| Qwen3 32B — the teacher for our mobile students | 3morixd | open | 0 | disc |
| Listed on OpenModelMap | duola15 | open | 0 | disc |
| TemporalMesh Transformer: 29.4 PPL at 48% compute — beats Mamba, new open-source architecture | vigneshwar234 | open | 0 | disc |
| Add LEXam evaluation results | joelniklaus | open | 0 | disc |
| original_max_position_embeddings for YaRN | XirenZhou | open | 0 | disc |
| WHEN WILL THE BASE MODEL BE RELEASED? WHEN WILL THE BASE MODEL BE RELEASED? WHEN WILL THE BASE MODEL BE RELEASED? | Linksome | open | 0 | disc |
| Update config.json | Pernekhan | closed | 0 | disc |
| When can we see the base model for Qwen3 32B? | arpitsh018 | open | 0 | disc |
| Will Qwen3-32B be updated just like Qwen3-235B-A22B? | Enigrand | open | 0 | disc |
| JSON formatting errors in Function Call scenarios | liopen | open | 0 | disc |
| qweb1 | MaxLin-un | draft | 0 | disc |
| MoE version with the same performance as this 32B dense | rtzurtz | open | 0 | disc |
| Low Score on GSM8K on lm-eval-harness? (just 74.91) | jvonrad | open | 0 | disc |
| Transformers version for qwen3-32B-8FP | as-il | open | 0 | disc |
| Where is the Base Model? | jvonrad | open | 0 | disc |
| I want to use this model to run my code | yunxi0827 | draft | 0 | disc |
| Qwen3-32B-Base? | canac84073 | open | 0 | disc |
| RuntimeError: probability tensor contains either `inf`, `nan` or element < 0 | VMoorjani | open | 0 | disc |
| Add assistant mask support to Qwen3-32B | waleko | open | 0 | disc |
| Setting 'enable_thinking=False' has no effect. | ktrocks | open | 0 | disc |
| finetune question | Saicy | open | 0 | disc |
| Performance problem: 32B 4x slower than 30B | jagusztinl | closed | 0 | disc |
| Qwen3ForCausalLM - Architecture issue | cr-gkn | open | 0 | disc |
| Request to Release the Base Model for Qwen3-32B | eramax | open | 0 | disc |
| How to control thinking length? | lidh15 | open | 0 | disc |
| Qwen3 does not deploy on Endpoints | zenfiric | open | 0 | disc |
| The model's instructions follow too poorly | xldistance | open | 0 | disc |
| Update README.md | Logical-Transcendence84 | open | 0 | disc |
| please release AWQ version | classdemo | open | 0 | disc |
| Collections of Bad Cases User Reviews and Comments of Qwen3 32B model | DeepNLP | open | 0 | disc |
| Potential issue with large context sizes - can someone confirm? | Thireus | open | 0 | disc |
| Qwen 3 presence of tools affect output length? | evetsagg | open | 0 | disc |
| "/no_think" control is unstable | Smorty100 | open | 0 | disc |
| ⛔ Censored on Chinese political regime topics. Sad for the model cohesion. | owao | closed | 0 | disc |
| LICENSE files missing | johndoe2001 | open | 0 | disc |
| After setting /nothinking or enable_thinking=False, can the empty <thinking> tag be omitted from the response? | pteromyini | open | 0 | disc |
| Feedback: It's a good model, however it hallucinates very badly at local facts (Germany) | Dampfinchen | open | 0 | disc |
| The correct way of fine-tuning on multi-turn trajectories | hr0nix | open | 0 | disc |
| Providing a GPTQ version | blueteamqq1 | open | 0 | disc |
| how to set, enable_thinking=False, on ollama | TatsuhiroC | open | 0 | disc |
| Maximum Token Length 40k？ | zhilinw6 | closed | 0 | disc |
| 🚀[Fine-tuning] Implementation and Best Practices for Qwen3 CPT/SFT/DPO/GRPO Training👋 | study-hjt | open | 0 | disc |
| Reasoning or Non-reasoning model? | dipta007 | open | 0 | disc |
| Local Installation Video and Testing - Step by Step | fahdmirzac | open | 0 | disc |
| 【Evaluation】Best practice for evaluating Qwen3 !! | wangxingjun778 | open | 0 | disc |
| Base Model? | Downtown-Case | open | 0 | disc |
| Is this multimodal? | pbarker | open | 0 | disc |
| Add languages tag | de-francophones | open | 0 | disc |