New model from Telperion: Qwen3.8-27B-MLA & Qwen3.8-27B-GLA-g2. 4x smaller KV cache, smarter, and more efficient reasoning.
英文标题：New model from Telperion: Qwen3.8-27B-MLA & Qwen3.8-27B-GLA-g2. 4x smaller KV cache, smarter, and more efficient reasoning.
Hello! We've been busy at Telperion with a lot of experimental research (more coming soon). Today, we're announcing the release of our latent attention variants of Qwen3.8-27B. Our latent attention variants (quants calibrated to FP8 KV cache) compress the KV cache by 4×, enabling a near 4× increase
中文
Hello! We've been busy at Telperion with a lot of experimental research (more coming soon). Today, we're announcing the release of our latent attention variants of Qwen3.8-27B. Our latent attention variants (quants calibrated to FP8 KV cache) compress the KV cache by 4×, enabling a near 4× increase
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
Hello! We've been busy at Telperion with a lot of experimental research (more coming soon). Today, we're announcing the release of our latent attention variants of Qwen3.8-27B. Our latent attention variants (quants calibrated to FP8 KV cache) compress the KV cache by 4×, enabling a near 4× increase