Qwen3-0.6B

Qwen3-0.6B is the most compact model in the series, containing 600 million parameters and supporting a context window of 32,000 tokens. The model is built on an architecture with 28 layers, featuring 16 attention heads for queries and 8 attention heads for keys and values, ensuring efficient use of computational resources while maintaining high-quality text processing. Despite its compact size, the model was trained on 36 trillion tokens and supports 119 languages and dialects, making it exceptionally versatile for its class.

The main advantage of Qwen3-0.6B is its outstanding efficiency combined with minimal resource requirements. It is specifically designed for deployment on mobile devices, edge computing platforms, and IoT applications, where low power consumption and fast inference are critical. Despite its small footprint, the model delivers impressive performance in general language understanding, simple dialogues, and basic text processing tasks.

Qwen3-0.6B is ideal for applications with strict memory and computational constraints: mobile app chatbots, embedded AI assistants, fast text processing systems, and fundamental NLP tasks such as text classification, information extraction, and automatic summarization.

Announce Date: 29.04.2025
Parameters: 0.6B
Context: 40K
Attention Type: Full or Sliding Window Attention
VRAM requirements: 4.7 GB using 4 bits quantization
Developer: Alibaba
Transformers Version: 4.51.0
Ollama Version: 0.6.6
License: Apache 2.0

Use our pre-built public endpoints to test inference and explore Qwen3-0.6B capabilities.

Rent your own physically dedicated instance with hourly or long-term monthly billing.

We recommend deploying private instances in the following scenarios:

• maximize endpoint performance,
• enable full context for long sequences,
• ensure top-tier security for data processing in an isolated, dedicated environment,
• use custom weights, such as fine-tuned models or LoRA adapters.

Contact our dedicated neural networks support team at nn@immers.cloud or send your request to the sales department at sale@immers.cloud.