← Back to Models

qwen3.5-4b

lmstudio-community/qwen3.5-4b

View on HuggingFace
Publisher
lmstudio-community
Architecture
qwen35
Parameters
4B
Quantization
Q4_K_M (4.0 bpw)
Format
gguf
Max Context
262k tokens
Type
llm
File Size
3.15 GB
Est. RAM
4.7 GB
Est. VRAM
4.7 GB
Capabilities
visiontrained_for_tool_use

Benchmark Results

Compare Models