Qwen3.5-27B

About

Qwen3.5-27B (Qwen/Qwen3.5-27B) is the mid-size unified vision-language foundation model of Alibaba's Qwen3.5 generation - 27B parameters (dense; FFN-based, no MoE), handling text, image and video input across 201 languages and dialects. Its 64-layer hybrid stack repeats 16x (3x (Gated DeltaNet -> FFN) + 1x (Gated Attention -> FFN)): 48 linear-attention layers (Gated DeltaNet, 48 V / 16 QK heads, head dim 128) and 16 full-attention layers (Gated Attention, 24 Q / 4 KV heads, head dim 256, RoPE dim 64), with hidden size 5120, FFN intermediate dimension 17408, 248K vocabulary, Multi-Token Prediction (MTP) trained with multi-steps, and a 262,144-token native context extensible to 1,010,000.

Qwen3.5's early fusion training on multimodal tokens achieves near-100% multimodal training efficiency versus text-only training and cross-generational parity with Qwen3 (outperforming Qwen3-VL across reasoning, coding, agents and visual understanding). Post-training scales RL across Million-agent RL environments with progressively complex task distributions for robust real-world adaptability, supported by next-generation asynchronous RL infrastructure. Released February 24, 2026 under Apache 2.0.

Training Data Pre-training on multimodal tokens (early fusion, near-100% multimodal training efficiency vs text-only); post-training with scaled RL across million-agent environments. 201 languages and dialects.