← Back to Models

gemma-4-e4b-it

gemma-4-e4b-it

Publisher
lmstudio-community
Architecture
gemma4
Parameters
7.5B
Quantization
Q4_K_M (4.0 bpw)
Format
gguf
Max Context
131k tokens
Type
llm
File Size
5.89 GB
Est. RAM
7.4 GB
Est. VRAM
7.4 GB
Capabilities
visiontrained_for_tool_use

Benchmark Results

Compare Models