← Back to Models

qwen3.5-9b-optiq

qwen3.5-9b-optiq

Publisher
mlx-community
Architecture
qwen3_5
Parameters
9B
Quantization
4bit (4.0 bpw)
Format
mlx
Max Context
262k tokens
Type
llm
File Size
5.65 GB
Est. RAM
7.1 GB
Est. VRAM
7.1 GB
Capabilities
trained_for_tool_use

Benchmark Results

Compare Models