← Back to Models

qwen3.5-4b

unsloth/qwen3.5-4b

View on HuggingFace
Publisher
unsloth
Architecture
qwen35
Parameters
4B
Quantization
Q4_K_S (4.0 bpw)
Format
gguf
Max Context
262k tokens
Type
llm
File Size
3.65 GB
Est. RAM
5.2 GB
Est. VRAM
5.2 GB
Capabilities
visiontrained_for_tool_use

Benchmark Results

Compare Models