HF model

mmnga / llm-jp-3-8x1.8b-instruct3-gguf

A gguf‑format conversion of llm-jp‑3‑8x1.8b‑instruct3, built with imatrix data from TFMC/imatrix‑dataset‑for‑japanese‑llm and runnable via llama.cpp with CUDA support.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
1,000
Hugging Face likes
1
Listed
Apr 1, 2025

Popular in the same category

Resources in similar research fields

Learn from slides & articles