Qwen 3.5 9B (MLX 4-bit) API
About
Integrate multimodal vision capabilities using Qwen 3.5 9B (MLX 4-bit), designed to process both text and images seamlessly. This model delivers available completely free of charge, native tool calling support, open weights architecture. Access Qwen 3.5 9B (MLX 4-bit) via the Atomic Chat API with up to 8K output tokens.
Capabilities
Input Modalities
textimage
Output Modalities
text
Reasoning
No
Structured Output
Limits
Context Window
33K
Tokens
Input Limit
33K
Tokens
Max Output
8K
Tokens
Pricing
Standard (per 1M tokens)
Input
Free
Output
Free
Frequently Asked Questions
Qwen 3.5 9B (MLX 4-bit) by Atomic Chat costs Free per 1M input tokens and Free per 1M output tokens.
Model Details
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
ATOMIC_CHAT_API_KEY
API Base URL
http://127.0.0.1:1337/v1