HF model

soyaakinohara / Spark-X2.5-4B-Heretic-jp-gguf

Japanese‑adapted Spark‑X2.5‑4B model (Heretic JP) with refusal attenuation, pretraining, instruction tuning and tool‑calling repair, available in GGUF quantizations from BF16 to Q4_K_M (~2.5 GiB), usable via llama.cpp for 1,048,576‑token context.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
589,000
Hugging Face likes
22
Listed
Sep 7, 2026

Downloads (30-day window) over time

0200k400k600kNovSepJulMayMarJan 2026589,000
Show as a table
MonthDL (30d)
Dec 2025—
Jan 2026—
Feb 2026—
Mar 2026—
Apr 2026—
May 2026—
Jun 2026—
Jul 2026—
Aug 2026—
Sep 20264,000
Oct 2026249,000
Nov 2026589,000

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

Popular in the same category

Resources in similar research fields

Learn from slides & articles