{"id":"model.alibaba.qwen.qwen3-235b-a22b","name":"Qwen3-235B-A22B","family":"Qwen3","type":"frontier","modalities":["text"],"capabilities":["agent"],"openness":{"weights":"open_weights","code":"not_disclosed","data":"partially_disclosed","license":null,"deployment":"self_hostable","api":null},"keySpecs":{"contextWindowTokens":32768,"extendedContextWindowTokens":null,"totalParameters":235,"activeParameters":null,"architectureType":null,"baseModel":null,"inputPriceUsdPerMtok":null,"outputPriceUsdPerMtok":null,"concurrencyLimitRequests":null},"organization":{"id":"org.alibaba-qwen","name":"阿里千问 / Qwen","websiteUrl":"https://qwen.ai/"},"brand":{"id":"brand.alibaba-qwen","name":"Qwen","websiteUrl":"https://qwen.ai"},"product":{"id":"product.alibaba-qwen.models","name":"Qwen Models","websiteUrl":"https://qwen.readthedocs.io/en/latest/"},"origin":"domestic","versions":[{"id":"version.alibaba.qwen.qwen3-235b-a22b","name":"Qwen3-235B-A22B","externalModelId":"Qwen/Qwen3-235B-A22B","kind":"date","releaseDate":"2025-04-29","datePrecision":"day","publicAvailableAt":null,"lifecycleStatus":"active","knowledgeCutoff":null,"claims":[{"id":"claim.version.alibaba.qwen.qwen3-235b-a22b.capability.agent","fieldKey":"capability_tags","value":{"value":["agent"]},"rawValue":"Qwen3 supports tool calling and agent capabilities","ingestionOrigin":"curated_official","unit":null,"condition":"Explicit public claim projection from agent; this is a documented capability tag, not a benchmark or quality conclusion.","status":"approved","confidence":"high","reviewedBy":"system:capability-projection","reviewedAt":"2026-08-05 09:26:02.481569+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.alibaba.qwen.docs","title":"Qwen documentation","url":"https://qwen.readthedocs.io/en/latest/","accessedAt":"2026-09-17 15:20:45.271+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-09-17 15:17:00.621+08"},"evidence":{"id":"evidence.alibaba.qwen.docs.context","locator":"Key Concepts and Qwen3-2507 documentation","excerpt":"Qwen documents 119 languages and dialects for Qwen3. For Qwen3-2507, the maximum assistant message length is 81,920 tokens for thinking models and 16,384 tokens for instruct models; Qwen3-2507 supports 256K context and can be extended to 1M tokens."}},{"id":"claim.version.alibaba.qwen.qwen3-235b.context","fieldKey":"context_window_tokens","value":{"unit":"tokens","value":32768},"rawValue":null,"ingestionOrigin":"curated_official","unit":"tokens","condition":"Re-verified on 2026-10-20 against the current model card: 32,768 tokens natively; 131,072 tokens only when YaRN RoPE scaling is enabled by the serving framework, so the native limit is recorded here.","status":"approved","confidence":"high","reviewedBy":"system:curated-publisher","reviewedAt":"2026-10-20 10:59:35.72022+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.alibaba.qwen.qwen3-235b","title":"Qwen3-235B-A22B model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B","accessedAt":"2026-09-17 15:20:51.339+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-09-17 15:17:03.584+08"},"evidence":{"id":"evidence.qwen.qwen3-235b-a22b.hf.2026-10-20","locator":"Hugging Face model card Qwen/Qwen3-235B-A22B (README.md), sections 'Qwen3-235B-A22B' features list, front-matter license, and 'Processing Long Texts'","excerpt":"Front matter: license: apache-2.0. Features list: Number of Parameters: 235B in total and 22B activated; Context Length: 32,768 natively and 131,072 tokens with YaRN. Long-text section: Qwen3 natively supports context lengths of up to 32,768 tokens, and the model's performance was validated up to 131,072 tokens using the YaRN method. The Hugging Face model API reports the repository as public, not gated and not disabled, and the repository exposes safetensors weights."}},{"id":"claim.version.alibaba.qwen.qwen3-235b.deployment","fieldKey":"deployment_options","value":["Transformers","vLLM","SGLang","Ollama","LM Studio","MLX-LM","llama.cpp","KTransformers"],"rawValue":"Official documentation and model card list Transformers, vLLM, SGLang and local deployment tools.","ingestionOrigin":"curated_official","unit":null,"condition":null,"status":"approved","confidence":"high","reviewedBy":"system:curated_official","reviewedAt":"2026-08-03 22:17:18.866955+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.alibaba.qwen.docs","title":"Qwen documentation","url":"https://qwen.readthedocs.io/en/latest/","accessedAt":"2026-09-17 15:20:45.271+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-09-17 15:17:00.621+08"},"evidence":{"id":"evidence.alibaba.qwen.docs.context","locator":"Key Concepts and Qwen3-2507 documentation","excerpt":"Qwen documents 119 languages and dialects for Qwen3. For Qwen3-2507, the maximum assistant message length is 81,920 tokens for thinking models and 16,384 tokens for instruct models; Qwen3-2507 supports 256K context and can be extended to 1M tokens."}},{"id":"claim.version.alibaba.qwen.qwen3-235b.languages","fieldKey":"language_count","value":{"unit":"languages and dialects","value":119},"rawValue":"119 languages and dialects","ingestionOrigin":"curated_official","unit":"languages","condition":null,"status":"approved","confidence":"high","reviewedBy":"system:curated_official","reviewedAt":"2026-08-03 22:13:04.249287+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.alibaba.qwen.qwen3.blog","title":"Qwen3: Think Deeper, Act Faster","url":"https://qwenlm.github.io/blog/qwen3/","accessedAt":"2026-09-17 15:20:54.384+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-09-17 15:17:03.59+08"},"evidence":{"id":"evidence.alibaba.qwen.qwen3.blog.models","locator":"Model tables and release metadata","excerpt":"Qwen states that Qwen3 was released on April 29, 2025, open-weights two MoE models and six dense models under Apache 2.0. The model tables list layers, attention heads, experts, and 128K context for the release family."}},{"id":"claim.version.alibaba.qwen.qwen3-235b-a22b.lifecycle-status","fieldKey":"lifecycle_status","value":{"value":"active"},"rawValue":null,"ingestionOrigin":"curated_official","unit":null,"condition":"Set on 2026-10-20 because the Qwen3-235B-A22B weights remain publicly downloadable from the official Hugging Face repository, which the API reports as neither gated nor disabled; Qwen does not publish a formal lifecycle table, so this reflects current availability rather than a vendor-stated status.","status":"approved","confidence":"high","reviewedBy":"system:curated-publisher","reviewedAt":"2026-10-20 10:59:35.72022+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.alibaba.qwen.qwen3-235b","title":"Qwen3-235B-A22B model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B","accessedAt":"2026-09-17 15:20:51.339+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-09-17 15:17:03.584+08"},"evidence":{"id":"evidence.qwen.qwen3-235b-a22b.hf.2026-10-20","locator":"Hugging Face model card Qwen/Qwen3-235B-A22B (README.md), sections 'Qwen3-235B-A22B' features list, front-matter license, and 'Processing Long Texts'","excerpt":"Front matter: license: apache-2.0. Features list: Number of Parameters: 235B in total and 22B activated; Context Length: 32,768 natively and 131,072 tokens with YaRN. Long-text section: Qwen3 natively supports context lengths of up to 32,768 tokens, and the model's performance was validated up to 131,072 tokens using the YaRN method. The Hugging Face model API reports the repository as public, not gated and not disabled, and the repository exposes safetensors weights."}},{"id":"claim.version.alibaba.qwen.qwen3-235b.license","fieldKey":"model_license","value":{"value":"Apache 2.0"},"rawValue":null,"ingestionOrigin":"curated_official","unit":null,"condition":"Re-verified on 2026-10-20; the model card front matter declares apache-2.0 and links the repository LICENSE file.","status":"approved","confidence":"high","reviewedBy":"system:curated-publisher","reviewedAt":"2026-10-20 10:59:35.72022+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.alibaba.qwen.qwen3-235b","title":"Qwen3-235B-A22B model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B","accessedAt":"2026-09-17 15:20:51.339+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-09-17 15:17:03.584+08"},"evidence":{"id":"evidence.qwen.qwen3-235b-a22b.hf.2026-10-20","locator":"Hugging Face model card Qwen/Qwen3-235B-A22B (README.md), sections 'Qwen3-235B-A22B' features list, front-matter license, and 'Processing Long Texts'","excerpt":"Front matter: license: apache-2.0. Features list: Number of Parameters: 235B in total and 22B activated; Context Length: 32,768 natively and 131,072 tokens with YaRN. Long-text section: Qwen3 natively supports context lengths of up to 32,768 tokens, and the model's performance was validated up to 131,072 tokens using the YaRN method. The Hugging Face model API reports the repository as public, not gated and not disabled, and the repository exposes safetensors weights."}},{"id":"claim.version.alibaba.qwen.qwen3-235b.post-training-methods","fieldKey":"post_training_methods","value":{"value":"Long CoT cold start; reasoning-based RL; thinking-mode fusion; general RL."},"rawValue":"Four-stage post-training pipeline","ingestionOrigin":"curated_official","unit":null,"condition":null,"status":"approved","confidence":"high","reviewedBy":"system:curated_official","reviewedAt":"2026-08-03 22:13:04.249287+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.alibaba.qwen.qwen3.blog","title":"Qwen3: Think Deeper, Act Faster","url":"https://qwenlm.github.io/blog/qwen3/","accessedAt":"2026-09-17 15:20:54.384+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-09-17 15:17:03.59+08"},"evidence":{"id":"evidence.alibaba.qwen.qwen3.blog.training","locator":"Pre-training and Post-training sections","excerpt":"Qwen states that Qwen3 uses approximately 36 trillion pre-training tokens across 119 languages and dialects. The pre-training process has three stages; post-training has four stages: long chain-of-thought cold start, reasoning-based reinforcement learning, thinking mode fusion, and general reinforcement learning."}},{"id":"claim.version.alibaba.qwen.qwen3-235b.pretraining-tokens","fieldKey":"pretraining_tokens","value":{"unit":"T","value":36},"rawValue":"Approximately 36 trillion pre-training tokens","ingestionOrigin":"curated_official","unit":"T","condition":null,"status":"approved","confidence":"high","reviewedBy":"system:curated_official","reviewedAt":"2026-08-03 22:13:04.249287+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.alibaba.qwen.qwen3.blog","title":"Qwen3: Think Deeper, Act Faster","url":"https://qwenlm.github.io/blog/qwen3/","accessedAt":"2026-09-17 15:20:54.384+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-09-17 15:17:03.59+08"},"evidence":{"id":"evidence.alibaba.qwen.qwen3.blog.training","locator":"Pre-training and Post-training sections","excerpt":"Qwen states that Qwen3 uses approximately 36 trillion pre-training tokens across 119 languages and dialects. The pre-training process has three stages; post-training has four stages: long chain-of-thought cold start, reasoning-based reinforcement learning, thinking mode fusion, and general reinforcement learning."}},{"id":"claim.version.alibaba.qwen.qwen3-235b.release-date","fieldKey":"release_date","value":{"value":"2025-04-29","precision":"day"},"rawValue":"April 29, 2025","ingestionOrigin":"curated_official","unit":null,"condition":null,"status":"approved","confidence":"high","reviewedBy":"system:curated_official","reviewedAt":"2026-08-03 22:13:04.249287+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.alibaba.qwen.qwen3.blog","title":"Qwen3: Think Deeper, Act Faster","url":"https://qwenlm.github.io/blog/qwen3/","accessedAt":"2026-09-17 15:20:54.384+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-09-17 15:17:03.59+08"},"evidence":{"id":"evidence.alibaba.qwen.qwen3.blog.models","locator":"Model tables and release metadata","excerpt":"Qwen states that Qwen3 was released on April 29, 2025, open-weights two MoE models and six dense models under Apache 2.0. The model tables list layers, attention heads, experts, and 128K context for the release family."}},{"id":"claim.version.alibaba.qwen.qwen3-235b.thinking","fieldKey":"thinking_modes","value":{"value":"hybrid: thinking and non-thinking"},"rawValue":"Seamless switching between thinking and non-thinking modes","ingestionOrigin":"curated_official","unit":null,"condition":null,"status":"approved","confidence":"high","reviewedBy":"system:curated_official","reviewedAt":"2026-08-03 22:13:04.249287+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.alibaba.qwen.qwen3.blog","title":"Qwen3: Think Deeper, Act Faster","url":"https://qwenlm.github.io/blog/qwen3/","accessedAt":"2026-09-17 15:20:54.384+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-09-17 15:17:03.59+08"},"evidence":{"id":"evidence.alibaba.qwen.qwen3.blog.models","locator":"Model tables and release metadata","excerpt":"Qwen states that Qwen3 was released on April 29, 2025, open-weights two MoE models and six dense models under Apache 2.0. The model tables list layers, attention heads, experts, and 128K context for the release family."}},{"id":"claim.version.alibaba.qwen.qwen3-235b.tool-calls","fieldKey":"tool_calls","value":{"value":true},"rawValue":"Qwen3 supports tool calling and agent capabilities","ingestionOrigin":"curated_official","unit":null,"condition":null,"status":"approved","confidence":"high","reviewedBy":"system:curated_official","reviewedAt":"2026-08-03 22:13:04.249287+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.alibaba.qwen.docs","title":"Qwen documentation","url":"https://qwen.readthedocs.io/en/latest/","accessedAt":"2026-09-17 15:20:45.271+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-09-17 15:17:00.621+08"},"evidence":{"id":"evidence.alibaba.qwen.docs.context","locator":"Key Concepts and Qwen3-2507 documentation","excerpt":"Qwen documents 119 languages and dialects for Qwen3. For Qwen3-2507, the maximum assistant message length is 81,920 tokens for thinking models and 16,384 tokens for instruct models; Qwen3-2507 supports 256K context and can be extended to 1M tokens."}},{"id":"claim.version.alibaba.qwen.qwen3-235b.total-parameters","fieldKey":"total_parameters","value":{"unit":"B","value":235},"rawValue":null,"ingestionOrigin":"curated_official","unit":"B","condition":"Re-verified on 2026-10-20; the model card states 235B total parameters with 22B activated per token.","status":"approved","confidence":"high","reviewedBy":"system:curated-publisher","reviewedAt":"2026-10-20 10:59:35.72022+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.alibaba.qwen.qwen3-235b","title":"Qwen3-235B-A22B model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B","accessedAt":"2026-09-17 15:20:51.339+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-09-17 15:17:03.584+08"},"evidence":{"id":"evidence.qwen.qwen3-235b-a22b.hf.2026-10-20","locator":"Hugging Face model card Qwen/Qwen3-235B-A22B (README.md), sections 'Qwen3-235B-A22B' features list, front-matter license, and 'Processing Long Texts'","excerpt":"Front matter: license: apache-2.0. Features list: Number of Parameters: 235B in total and 22B activated; Context Length: 32,768 natively and 131,072 tokens with YaRN. Long-text section: Qwen3 natively supports context lengths of up to 32,768 tokens, and the model's performance was validated up to 131,072 tokens using the YaRN method. The Hugging Face model API reports the repository as public, not gated and not disabled, and the repository exposes safetensors weights."}},{"id":"claim.version.alibaba.qwen.qwen3-235b.training-data-transparency","fieldKey":"training_data_transparency","value":{"value":"partially_disclosed"},"rawValue":"Qwen discloses aggregate token count, language coverage and data construction methods, not the full dataset.","ingestionOrigin":"curated_official","unit":null,"condition":null,"status":"approved","confidence":"high","reviewedBy":"system:curated_official","reviewedAt":"2026-08-03 22:17:18.866955+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.alibaba.qwen.qwen3.blog","title":"Qwen3: Think Deeper, Act Faster","url":"https://qwenlm.github.io/blog/qwen3/","accessedAt":"2026-09-17 15:20:54.384+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-09-17 15:17:03.59+08"},"evidence":{"id":"evidence.alibaba.qwen.qwen3.blog.training","locator":"Pre-training and Post-training sections","excerpt":"Qwen states that Qwen3 uses approximately 36 trillion pre-training tokens across 119 languages and dialects. The pre-training process has three stages; post-training has four stages: long chain-of-thought cold start, reasoning-based reinforcement learning, thinking mode fusion, and general reinforcement learning."}},{"id":"claim.version.alibaba.qwen.qwen3-235b.training-methods","fieldKey":"training_methods","value":{"value":"Three-stage pretraining: S1 over 30T tokens at 4K context; S2 adds 5T knowledge-intensive data; S3 uses high-quality long-context data to extend context to 32K."},"rawValue":"Three-stage pretraining","ingestionOrigin":"curated_official","unit":null,"condition":null,"status":"approved","confidence":"high","reviewedBy":"system:curated_official","reviewedAt":"2026-08-03 22:13:04.249287+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.alibaba.qwen.qwen3.blog","title":"Qwen3: Think Deeper, Act Faster","url":"https://qwenlm.github.io/blog/qwen3/","accessedAt":"2026-09-17 15:20:54.384+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-09-17 15:17:03.59+08"},"evidence":{"id":"evidence.alibaba.qwen.qwen3.blog.training","locator":"Pre-training and Post-training sections","excerpt":"Qwen states that Qwen3 uses approximately 36 trillion pre-training tokens across 119 languages and dialects. The pre-training process has three stages; post-training has four stages: long chain-of-thought cold start, reasoning-based reinforcement learning, thinking mode fusion, and general reinforcement learning."}},{"id":"claim.version.alibaba.qwen.qwen3-235b.weights","fieldKey":"weights_availability","value":{"value":"open_weights"},"rawValue":null,"ingestionOrigin":"curated_official","unit":null,"condition":"Re-verified on 2026-10-20; the Hugging Face repository for Qwen3-235B-A22B is public, not gated and exposes safetensors weights, so the open weights remain downloadable.","status":"approved","confidence":"high","reviewedBy":"system:curated-publisher","reviewedAt":"2026-10-20 10:59:35.72022+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.alibaba.qwen.qwen3-235b","title":"Qwen3-235B-A22B model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B","accessedAt":"2026-09-17 15:20:51.339+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-09-17 15:17:03.584+08"},"evidence":{"id":"evidence.qwen.qwen3-235b-a22b.hf.2026-10-20","locator":"Hugging Face model card Qwen/Qwen3-235B-A22B (README.md), sections 'Qwen3-235B-A22B' features list, front-matter license, and 'Processing Long Texts'","excerpt":"Front matter: license: apache-2.0. Features list: Number of Parameters: 235B in total and 22B activated; Context Length: 32,768 natively and 131,072 tokens with YaRN. Long-text section: Qwen3 natively supports context lengths of up to 32,768 tokens, and the model's performance was validated up to 131,072 tokens using the YaRN method. The Hugging Face model API reports the repository as public, not gated and not disabled, and the repository exposes safetensors weights."}}],"benchmarks":[]}],"dataUpdatedAt":"2026-10-20 10:59:35.72022+08","latestVersion":{"id":"version.alibaba.qwen.qwen3-235b-a22b","name":"Qwen3-235B-A22B","externalModelId":"Qwen/Qwen3-235B-A22B","status":"active"},"dataQuality":{"approved":15,"pending":0,"stale":8,"conflicted":0},"availabilityRegions":[],"availabilityChannels":[],"availabilityScopes":[],"decisionReadiness":{"overall":"A","evaluatedAt":"2026-11-01T12:11:54.406Z","tracks":[{"key":"api","applicable":false,"grade":"incomplete","verifiedAt":null,"satisfiedFields":[],"missingFields":[],"missingEvidenceFields":[],"staleFields":[],"conflictedFields":[],"ineligibleSourceFields":[],"reasons":[],"fields":[]},{"key":"self_hosted","applicable":true,"grade":"A","verifiedAt":"2026-09-17 15:20:45.271+08","satisfiedFields":["release_date","lifecycle_status","capability_tags","deployment_options","context_window_tokens","weights_availability","model_license","total_parameters"],"missingFields":[],"missingEvidenceFields":[],"staleFields":[],"conflictedFields":[],"ineligibleSourceFields":[],"reasons":[],"fields":[{"fieldKey":"release_date","status":"satisfied","verifiedAt":"2026-09-17 15:20:54.384+08","expiresAt":"2026-12-16T07:20:54.384Z"},{"fieldKey":"lifecycle_status","status":"satisfied","verifiedAt":"2026-10-20 10:59:35.72022+08","expiresAt":"2026-11-19T02:59:35.720Z"},{"fieldKey":"capability_tags","status":"satisfied","verifiedAt":"2026-09-17 15:20:45.271+08","expiresAt":"2026-12-16T07:20:45.271Z"},{"fieldKey":"deployment_options","status":"satisfied","verifiedAt":"2026-09-17 15:20:45.271+08","expiresAt":"2026-12-16T07:20:45.271Z"},{"fieldKey":"context_window_tokens","status":"satisfied","verifiedAt":"2026-10-20 10:59:35.72022+08","expiresAt":"2027-01-18T02:59:35.720Z"},{"fieldKey":"weights_availability","status":"satisfied","verifiedAt":"2026-10-20 10:59:35.72022+08","expiresAt":"2026-11-19T02:59:35.720Z"},{"fieldKey":"model_license","status":"satisfied","verifiedAt":"2026-10-20 10:59:35.72022+08","expiresAt":"2027-01-18T02:59:35.720Z"},{"fieldKey":"total_parameters","status":"satisfied","verifiedAt":"2026-10-20 10:59:35.72022+08","expiresAt":"2027-01-18T02:59:35.720Z"}]}]},"timeline":[{"id":"timeline.version.version.alibaba.qwen.qwen3-235b-a22b","kind":"version","subjectId":"version.alibaba.qwen.qwen3-235b-a22b","date":"2025-04-29","datePrecision":"day","title":"Qwen3-235B-A22B","summary":"模型版本 · active","eventType":"version","lifecycleStatus":"active","source":null},{"id":"event.alibaba.qwen.qwen3-235b.release","kind":"event","subjectId":"model.alibaba.qwen.qwen3-235b-a22b","date":"2025-04-29","datePrecision":"day","title":"Qwen3-235B-A22B 发布","summary":"Qwen 官方发布 Qwen3，并将 Qwen3-235B-A22B 作为旗舰 MoE 模型。","eventType":"release","lifecycleStatus":null,"source":{"id":"source.alibaba.qwen.qwen3.blog","title":"Qwen3: Think Deeper, Act Faster","url":"https://qwenlm.github.io/blog/qwen3/"}}],"availability":[],"enterpriseCases":[],"useCases":[],"deploymentProfiles":[],"learningResources":[],"trainingProfiles":[{"id":"training-profile.llamafactory.qwen3-235b.887b850","modelId":"model.alibaba.qwen.qwen3-235b-a22b","modelName":"Qwen3-235B-A22B","versionId":"version.alibaba.qwen.qwen3-235b-a22b","versionName":"Qwen3-235B-A22B","tool":"llamafactory","toolRef":"887b850813d80a8d893ec56703d5b3a0eec46de6","supportStatus":"supported","template":"qwen3","trainingStages":["sft","dpo","kto","orpo","simpo"],"tuningMethods":["full","freeze","lora","qlora"],"modalities":["text"],"modelLocator":"YOUR_QWEN3_MODEL_PATH","notes":"README 的 Qwen3 模型表与 qwen3/qwen3_nothink 模板说明支持该工具适配；思考与非思考版本必须选择相应模板。","verifiedAt":"2026-08-09 00:00:00+08","source":{"id":"source.llamafactory.readme.2026-08-09","title":"LlamaFactory README（固定 887b850 工具快照）","url":"https://github.com/hiyouga/LlamaFactory/blob/887b850813d80a8d893ec56703d5b3a0eec46de6/README_zh.md"},"evidence":{"id":"evidence.llamafactory.readme.models.2026-08-09","locator":"README：模型表、模板说明与训练方法","excerpt":"LlamaFactory README names DeepSeek 3-3.2 with template deepseek3, Llama 4 with template llama4, Qwen3 with templates qwen3/qwen3_nothink, and lists pretraining, SFT, reward-model, PPO, DPO, KTO, ORPO and SimPO training methods. It states that instruct/chat models must use their corresponding template."}}],"publication":{"approvedClaimsOnly":true,"note":"页面只展示已审核 Claim；待审核数据不会被当作公开事实。"}}