← Back to Models

gemma-3-4b

google/gemma-3-4b

View on HuggingFace
Publisher
google
Architecture
gemma3
Parameters
4B
Quantization
4bit (4.0 bpw)
Format
mlx
Max Context
131k tokens
Type
llm
File Size
2.83 GB
Est. RAM
4.3 GB
Est. VRAM
4.3 GB
Capabilities
vision

Benchmark Results

Compare Models