Home
About
Pricing
Documentation
Articles
Early Access
gemma-4-12b-it-GGUF
Home
/
Recommended Models
/ gemma-4-12b-it-GGUF
gemma-4-12b-it-GGUF
Author
unsloth
Parameters
12B
Quantization
Q4_K_M
Format
GGUF
License
apache-2.0
File size
6.63 GB
Use on Infersec
View on HuggingFace
Overview
Read our How to
Run Gemma 4 12B Guide!
Strengths
MBPP+
: 80.4% (304/378)
BFCL
(tool calling): 64.8% (400 problems)
Tested Hardware
Benchmarked by Infersec on:
NVIDIA RTX 5090
(64 GB RAM, 32 GB VRAM, linux)
Benchmark Runs
Performance and quality results across different hardware configurations
NVIDIA RTX 5090
64 GB RAM
linux
c=2 p=1
100.3 tok/s
MBPP+ 80.4% · BFCL 64.8%
Scroll to top