HF model

dahara1 / gemma-4-E2B-it-UD-japanese-imatrix

A GGUF‑converted Gemma‑4‑E2B‑it model fine‑tuned for Japanese proficiency, built with Unsloth® Dynamic Quantization 2.0, community bug fixes, Japanese calibration data, and runnable on a CPU (≥8 GB RAM, ≥4 GB disk) via llama.cpp.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
4,000
Hugging Face likes
3
Listed
May 5, 2026

Downloads (30-day window) over time

02k4k6kNovSepJulMayMarJan 20264,000
Show as a table
MonthDL (30d)
Dec 2025—
Jan 2026—
Feb 2026—
Mar 2026—
Apr 2026—
May 20266,000
Jun 20262,000
Jul 20261,000
Aug 20263,000
Sep 20263,000
Oct 20263,000
Nov 20264,000

Downloads over the 30 days before the last snapshot of each month.

Popular in the same category