gguf-quantization

gguf-quantization is a skill for Claude Code, Codex from Heldinhow/hermes-agent-skills. It costs 48 tokens per session (3,154 once invoked), scanned A, original, no licence file.

A skill for GGUF model files and llama.cpp quantization, which reduces a model's numerical precision to use less memory. It covers 2-bit to 8-bit quantization for running models on CPUs, GPUs, and Apple Silicon.

In plain words
What is it for?
Use it to prepare models for CPU or GPU inference, Apple Silicon systems, and deployments where flexible 2-8 bit quantization is needed.
Why use it?
It helps deploy language models on consumer hardware when full-precision versions need more memory or specialised hardware.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

Good fit Use it to prepare models for CPU or GPU inference, Apple Silicon systems, and deployments where flexible 2-8 bit quantization is needed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/heldinhow/hermes-agent-skills/gguf
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Heldinhow/hermes-agent-skills --skill gguf
Clone the repo
git clone --depth 1 https://github.com/Heldinhow/hermes-agent-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for gguf-quantization

README.md
[![agentmods](https://agentmods.dev/badge/skills/heldinhow/hermes-agent-skills/gguf/github.svg)](https://agentmods.dev/skills/heldinhow/hermes-agent-skills/gguf)
Your own site
<a href="https://agentmods.dev/skills/heldinhow/hermes-agent-skills/gguf"><img src="https://agentmods.dev/badge/skills/heldinhow/hermes-agent-skills/gguf/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for gguf-quantization

Your own site · 80×15
<a href="https://agentmods.dev/skills/heldinhow/hermes-agent-skills/gguf"><img src="https://agentmods.dev/badge/skills/heldinhow/hermes-agent-skills/gguf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,154 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.03154
Opus 5 $0.00024 $0.01577
Sonnet 5 $0.00010 $0.00631
Haiku 4.5 $0.00005 $0.00315

Measured 10d ago against content hash 719b2bbe316d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

gguf-quantization scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

mlops/inference/gguf/SKILL.md · 431 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 431 lines · 48 tokens per session scan A 719b2bbe316d

Subscribe to this mod's changes

gguf-quantization is a skill published in the GitHub repository Heldinhow/hermes-agent-skills (2 stars, last pushed 4mo ago), with no licence file. It adds 48 tokens to every session and 3,154 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

spark-environment-setup

Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.

wshobson/agents · 76 tokens

spark-memory-thermal-ops

Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.

wshobson/agents · 59 tokens

spark-training-gotchas

Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.

wshobson/agents · 63 tokens

llama-cpp

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

davila7/claude-code-templates · 76 tokens

minicpm5-deploy-vllm-ascend

Deploy MiniCPM5-2B with vLLM on Huawei Ascend NPU using vLLM-Ascend. Use when the user mentions vLLM-Ascend, Ascend NPU, Huawei Ascend, CANN, torchnpu, davinci devices, or wants an OpenAI-compatible MiniCPM5 server on Ascend hardware.

OpenBMB/MiniCPM · 87 tokens

amc-run-video-calibration

Calibrates pre-recorded cam.mp4 datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s; route live RTSP streams to amc-run-rtsp-calibration.

NVIDIA/skills · 57 tokens