HF model

elyza / Llama-3-ELYZA-JP-8B-GGUF

Llama‑3‑ELYZA‑JP‑8B is a Japanese‑enhanced 8‑B Llama 3 model with GGUF (Q4_K_M) and AWQ quantization, ready to run via llama.cpp, LM Studio, or an OpenAI‑compatible API.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
3,000
Hugging Face likes
76
Listed
Jun 27, 2024

Downloads (30-day window) over time

2k3k4k5kNovSepJulMayMarJan 20263,000
Show as a table
MonthDL (30d)
Dec 20255,000
Jan 20263,000
Feb 20262,000
Mar 20263,000
Apr 20262,000
May 20263,000
Jun 20262,000
Jul 20263,000
Aug 20262,000
Sep 20263,000
Oct 20263,000
Nov 20263,000

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

Popular in the same category

Resources in similar research fields