← Back to Models

gemma-4-31b-it

gemma-4-31b-it

Publisher
lmstudio-community
Architecture
gemma4
Parameters
31B
Quantization
Q4_K_M (4.0 bpw)
Format
gguf
Max Context
262k tokens
Type
llm
File Size
18.52 GB
Est. RAM
20.0 GB
Est. VRAM
20.0 GB
Capabilities
visiontrained_for_tool_use

Benchmark Results

Compare Models