← All skills
gguf
65 / 100 · Review before installing
Check before installing.
By graniet/kheish (GitHub) · other · 213 stars · scanned at commit df50433
GGUF format and llama.cpp quantization for efficient CPU/GPU inference.
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
The author does not mention this.
Found in 17 places.
Show 14 more
- skills/mlops/inference/gguf/SKILL.md, line 113
./llama-cli -m model-q4_k_m.gguf -p "Hello, how are you?" - skills/mlops/inference/gguf/SKILL.md, line 155
huggingface-cli download meta-llama/Llama-3.1-8B --local-dir ./llama-3.1-8b - skills/mlops/inference/gguf/SKILL.md, line 173
python convert_hf_to_gguf.py ./model --outfile model-f16.gguf - skills/mlops/inference/gguf/SKILL.md, line 201
MODEL="llama-3.1-8b-f16.gguf" - skills/mlops/inference/gguf/SKILL.md, line 287
./llama-server -m model-q4_k_m.gguf \ - skills/mlops/inference/gguf/SKILL.md, line 325
make clean && make GGML_METAL=1 - skills/mlops/inference/gguf/SKILL.md, line 342
make clean && make GGML_CUDA=1 - skills/mlops/inference/gguf/SKILL.md, line 355
make clean && make - skills/mlops/inference/gguf/SKILL.md, line 375
cat > Modelfile << 'EOF' - skills/mlops/inference/gguf/SKILL.md, line 401
cp model-q4_k_m.gguf text-generation-webui/models/ - skills/mlops/inference/gguf/SKILL.md, line 421
./llama-cli -m model.gguf --mmap - skills/mlops/inference/gguf/SKILL.md, line 427
./llama-cli -m model.gguf -ngl 20 # Reduce from 35 - skills/mlops/inference/gguf/SKILL.md, line 436
./llama-imatrix -m model-f16.gguf -f calibration.txt -o model.imatrix - skills/mlops/inference/gguf/references/advanced-usage.md, line 165
result = subprocess.run(
Downloads and installs other software
The author does not mention this.
Found in 8 places.
Show 5 more
Can call paid AI services billed to you
The author does not mention this.
Found in 2 places.
Sends data to these websites: api.openai.com
The author does not mention this.
Found in 2 places.
Safer alternatives
Low-risk skills in the same category (other) that look related. Check that one does what you need.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'gguf' ] || [ -L ~/.agents/skills/'gguf' ]; then echo 'A skill folder named gguf already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/graniet/kheish' "$d" && git -C "$d" checkout --quiet 'df50433f8d577f832c6812b9e67be8ddb766059d' -- 'skills/mlops/inference/gguf' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/mlops/inference/gguf' ~/.agents/skills/'gguf' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'gguf' ~/.claude/skills/'gguf' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for graniet/kheish shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/graniet/kheish/)
Score history
| Date | Version | Score |
|---|
| 2026-11-12 | df50433 | 65 |