HF model

mmnga / llm-jp-3-3.7b-instruct3-gguf

A GGUF‑converted Japanese LLM (llm‑jp‑3‑3.7b‑instruct3) built from imatrix data, usable with llama.cpp for inference on CUDA, and compatible with the listed 3‑model variants.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
2,000
Hugging Face likes
1
Listed
Jul 29, 2025

Popular in the same category

Resources in similar research fields

Learn from slides & articles