amazon / Mamba2-primed-HQwen3-8B-Instruct
Text Generation8.5B29310Updated Sep 19, 2026
Downloads
293
Likes
10
Last updated
Sep 19, 2026
License
apache-2.0
Mamba2-primed-HQwen3-8B-Instruct is a Hybrid language model consisting of 50% Attention layers and 50% Mamba2 layers, primed from Qwen3-8B using the Hybrid Model Factory Priming pipeline. The model is instruction-tuned and supports context lengths up to 128K tokens.
Tasks & library
- text generation
- transformers
Tags
- transformers
- hybrid_qwen3
- text-generation
- hybrid
- ssm
- state-space-model