Qwen3-4B-Instruct-2507-GPTQ-Int8

Compared to earlier quantized versions, the new quantized model demonstrates better tokens/s efficiency. This improvement comes from setting desc_act=False in the quantization configuration. We introduce the updated version of the **Qwen3-4B non-thinking mode**, named **Qwen3-4B-Instruct-2507**, featuring the following key enhancements: **Qwen3-4B-Instruct-2507** has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Number of Parameters: 4.0B - Number of Paramaters (Non-Embedding): 3.6B - Number of Layers: 36 - Number of Attention Heads (GQA): 32 for Q and 8 for KV - Context Length: **262,144 natively**.

译文尚未就绪，显示来源原文