Technical Specifications

System Requirements

VRAM requirements for different quantization methods and context sizes

Qwen3-1.7B

Qwen3-1.7B is a dense causal language model developed by Alibaba's Qwen Team, introduced as a component of the Qwen3 series on April 29, 2025. This model is engineered for general-purpose language tasks, distinguishing itself with a compact 1.7 billion parameter count. Its architecture is optimized for efficient operation across various hardware configurations, encompassing environments with constrained resources and edge devices. The model supports an extensive context length of 32,768 tokens, allowing it to process substantial documents and multi-turn conversations effectively.

Architecturally, Qwen3-1.7B is constructed with 28 transformer layers. It employs Grouped Query Attention (GQA) with 16 query heads and 8 key-value heads. The model integrates Rotary Positional Embeddings (RoPE), specifically enhanced with ABF-RoPE, to maintain positional information accuracy across its extended context length. Further architectural refinements include the implementation of qk layernorm and RMSNorm with pre-normalization for stable training. The activation function utilized within its layers is SwiGLU.

A distinguishing operational feature within the Qwen3 series, including the 1.7B variant, is its dual operational modes: "Thinking Mode" and "Non-Thinking Mode." The Thinking Mode facilitates complex logical reasoning tasks, such as mathematical problem-solving and code generation, through a step-by-step reasoning process. Conversely, the Non-Thinking Mode provides rapid, direct responses suitable for general conversational applications. This hybrid approach enables dynamic switching between modes, optimizing performance based on task complexity and efficiency requirements. Qwen3-1.7B demonstrates multilingual support, processing over 100 languages and dialects, and features agent capabilities for tool integration.

No evaluation benchmarks for Qwen3-1.7B available.