Hugging Face · #477

XHToken/Spark-X2.6-4B-GGUF

XHToken/Spark-X2.6-4B-GGUF is a GGUF text-generation model you can run locally. Run locally: llama-cli -hf XHToken/Spark-X2.6-4B-GGUF or ollama run hf.co/XHToken/Spark-X2.6-4B-GGUF. 221 Hugging Face likes (#477 in this directory).

Model
https://huggingface.co/XHToken/Spark-X2.6-4B-GGUF
Author
XHToken
Likes
221
Hub trending
#29 on this snapshot
Downloads (30 days)
147,273
Task
text-generation
Library
transformers
License
apache-2.0
Gated
No
Created
2026-10-19
Last modified
2026-10-27
Base models
XHToken/Spark-X2.6-4B
Snapshot
2026-10-29

Run it locally.

Shadowfetch Linux is a Debian testing desktop with KDE Plasma, local AI tools, and ShadowCode. ShadowCode's bundled llama.cpp runs GGUF models; you can also use llama.cpp or Ollama from the terminal.

llama.cpp

llama-cli -hf XHToken/Spark-X2.6-4B-GGUF

Ollama

ollama run hf.co/XHToken/Spark-X2.6-4B-GGUF

llama-cli -hf is Hugging Face's documented llama.cpp path for a Hub GGUF repo. ollama run hf.co/... is the documented Ollama path. Neither command invents a quant filename; the tool picks a file the repo actually publishes.

ShadowCode prompt.

Paste this into ShadowCode after you open Settings › Local models.

In Settings › Local models, add XHToken/Spark-X2.6-4B-GGUF from Hugging Face as a GGUF on this computer. Ask before downloading. Use the repo's published GGUF files; do not guess a quant filename.

Download Shadowfetch Linux — ISO, checksum and signature.

Back to Hugging Face models · Methodology