Qwen3 6 27b
First open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive...
Fonte do modelo
- Tipo
- Other
- Tamanho do arquivo
- 6,39–9,95 GB
- Modelo base
- Qwen3
- Versão
- vRevision b8fe2a0
- Atualizado
- 2 de out. de 2026
- Publicador
- @keras
- Downloads
- 36
- Parâmetros
- 27B
- Tarefas
- Geração de texto
- Fonte
- Hugging Face
Descrição da fonte
Model Overview
Model Summary
##Description
First open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience. As a native vision-language model, demonstrates outstanding results across a full range of benchmark evaluations, including reasoning, coding, agent capabilities, and multimodal understanding, empowering developers and enterprises to achieve significantly greater productivity. Built on an innovative hybrid architecture that fuses linear attention (via Gated Delta Networks) with a sparse mixture-of-experts, the model attains remarkable inference efficiency.
Qwen3.6 Highlights
Qwen3.6 features the following enhancement:
Unified Vision-Language Foundation: Early fusion training on multimodal tokens achieves cross-generational parity with Qwen3 and outperforms Qwen3-VL models across reasoning, coding, agents, and visual understanding benchmarks.
Efficient Hybrid Architecture: Gated Delta Networks combined with sparse Mixture-of-Experts deliver high-throughput inference with minimal latency and cost overhead.
Scalable RL Generalization: Reinforcement learning scaled across million-agent environments with progressively complex task distributions for robust real-world adaptability.
Global Linguistic Coverage: Expanded support to 201 languages and dialects, enabling inclusive, worldwide deployment with nuanced cultural and regional understanding.
Next-Generation Training Infrastructure: Near-100% multimodal training efficiency compared to text-only training and asynchronous RL frameworks supporting massive-scale agent scaffolds and environment orchestration.
For more details, please refer to Qwen3.6 Blog, GitHub.
Weights are released under the Apache 2 License . Keras model code is released under the Apache 2 License.
Links
- [Qwen3.6 Quickstart Notebook]( coming soon..!)
- Qwen3.6 API Documentation
- Qwen3.6 Model Card
- KerasHub Beginner Guide
- KerasHub Model Publishing Guide
Installation
Keras and KerasHub can be installed with:
pip install -U -q keras-hub
pip install -U -q keras
JAX, TensorFlow, and Torch come pre-installed in Kaggle Notebooks. For instructions on installing them in another environment, see the Keras Getting Started page.
Presets
The following model checkpoints are provided by the Keras team. For each of the presets, we provide code examples in the tab below:
| Preset Name | Parameters | Description |
|---|---|---|
| qwen3_6_27b | 27 Billion | Instruction-tuned 27B model. Delivers highly efficient,top-tier performance for complex reasoning,advanced coding, and extensive multilingual tasks. Optimized for fast inference and extended context lengths. |
Fontes
1 fonte
Fontes
1 fonteVerificado 2 de out.
Artefatos de modelo
11 artefatos
Artefatos de modelo
11 artefatosTrechos de fonte
3 trechos
Trechos de fonte
3 trechos--- library_name: keras-hub pipeline_tag: text-generation --- ### Model Overview # Model Summary ##**Description** First open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience. As a native vision-language model, demonstrates outstanding results across a full range of benchmark evaluations, including reasoning, coding, agent capabilities, and multimodal understanding, empowering developers and enterprises to achieve significantly greater productivity. Built on an innovative hybrid architecture that fuses linear attention (via Gated Delta Networks) with a sparse mixture-of-experts, the model attains remarkable inference efficiency. ## Qwen3.6 Highlights **Qwen3.6 features the following enhancement:** **Unified Vision-Language Foundation:** Early fusion training on multimodal tokens achieves cross-generational parity with Qwen3 and outperforms Qwen3-VL models across reasoning, coding, agents, and visual understanding benchmarks. **Efficient Hybrid Architecture:** Gated Delta Networks combined with sparse Mixture-of-Experts deliver high-throughput inference with minimal latency and cost overhead. **Scalable RL Generalization:** Reinforcement learning scaled across million-agent environments with progressively complex task distributions for robust real-world adaptability. **Global Linguistic Coverage:** Expanded support to 201 languages and dialects, enabling inclusive, worldwide deployment with nuanced cultural and regional understanding. **Next-Generation Training Infrastructure:** Near-100% multimodal training efficiency compared to text-only training and asynchronous RL frameworks supporting massive-scale agent scaffolds and environment orchestration. For more details, please refer to Qwen3.6 [Blog](https://qwen.ai/blog?id=qwen3.6), [GitHub](https://github.com/keras-team/keras-hub/tree/master/keras_hub/src/models/qwen3_5). Weights are released under the [Apache 2 License](https://github.com/keras-team/keras-hub/blob/master/LICENSE) . Keras model code is released under the [Apache 2 License](https://github.com/keras-team/keras-hub/blob/master/LICENSE). ## Links * [Qwen3.6 Quickstart Notebook]( coming soon..!) * [Qwen3.6 API Documentation](https://keras.io/keras_hub/api/models/qw...
--- library_name: keras-hub pipeline_tag: text-generation --- ### Model Overview
Source context: 36 downloads · 0 likes · Pipeline text-generation · Library keras-hub · Repo keras/qwen3_6_27b
