← Back to Models

qwen3.5-2b

qwen3.5-2b

Publisher
mlx-community
Architecture
qwen3_5
Parameters
2B
Quantization
4bit (4.0 bpw)
Format
mlx
Max Context
262k tokens
Type
llm
File Size
1.63 GB
Est. RAM
3.1 GB
Est. VRAM
3.1 GB
Capabilities
visiontrained_for_tool_use

Benchmark Results

Compare Models