local-inference-optimizer

local-inference-optimizer is a skill for Claude Code, Codex from yamaru-eu/hardware-probe. It costs 23 tokens per session (714 once invoked), scanned A, original, Apache-2.0.

A troubleshooting guide for running language models on your own computer with tools such as Ollama, LM Studio, or vLLM.

In plain words
What is it for?
It is for checking memory bandwidth, graphics memory, model size, and compression settings when choosing or tuning local models.
Why use it?
It helps explain slow responses, GPU not being used, and whether a model will fit in available memory.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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.

agentmods
npx agentmods add skills/yamaru-eu/hardware-probe/local-inference-optimizer
Any agent
npx skills add yamaru-eu/hardware-probe --skill local-inference-optimizer
Clone the repo
git clone --depth 1 https://github.com/yamaru-eu/hardware-probe

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 local-inference-optimizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/yamaru-eu/hardware-probe/local-inference-optimizer.svg)](https://agentmods.dev/skills/yamaru-eu/hardware-probe/local-inference-optimizer)
Your own site
<a href="https://agentmods.dev/skills/yamaru-eu/hardware-probe/local-inference-optimizer"><img src="https://agentmods.dev/badge/skills/yamaru-eu/hardware-probe/local-inference-optimizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 714 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original 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 $0.00023 $0.00714
Opus 5 $0.00012 $0.00357
Sonnet 5 $0.00005 $0.00143
Haiku 4.5 $0.00002 $0.00071

Measured 6d ago against content hash ab731d5d14aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

local-inference-optimizer 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 6d 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.

skills/local-inference-optimizer/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Local Inference Optimizer

Expert system for analyzing local hardware/software topology and providing actionable recommendations for LLM inference (Ollama, LM Studio, vLLM).

Context

Use this skill when a user wants to:

  1. Optimize their machine for local LLMs.
  2. Troubleshoot slow inference speeds.
  3. Understand why a model isn't using the GPU.
  4. Calculate if a specific model/quantization will fit.

Diagnostic Protocol

1. Memory Bandwidth Analysis

  • Rule: Inference speed is directly bound by Memory Bandwidth (GB/s).
  • Heuristics:
    • < 20 GB/s: Slow (CPU/Single Channel DDR4). Recommend small models (3B) or hardware upgrade.
    • 20-60 GB/s: Standard (Dual Channel DDR4/DDR5). Good for 7B-14B models.
    • 100 GB/s: High Performance (Apple M-Series, Quad Channel, or High-end GPU VRAM).

  • Advice: If memory_bandwidth_gbs is significantly lower than theoretical specs, suggest checking RAM slots (Dual Channel) or BIOS XMP/EXPO profiles.

2. VRAM & Quantization Strategy

  • Rule: Model + KV Cache must fit in VRAM for 10x speedup.
  • Formulas:
    • ModelSize = (Params * Quant) / 8 (e.g., 7B @ 4-bit ≈ 3.5GB).
    • KVCache = ContextLength * Params * 0.0000006 (Rough estimate).
  • Optimization: If VRAM is tight, suggest reducing num_ctx (context length) before dropping quantization quality.

3. Runtime Troubleshooting (WSL/Docker/Ollama)

  • WSL2: If memory_limit_gb in .wslconfig is < 50% of total RAM, suggest increasing it.
  • Docker: If hasNvidiaRuntime is false, provide the nvidia-container-toolkit installation steps.
  • Environment: If OLLAMA_NUM_PARALLEL is missing, suggest setting it to 2 for multi-agent workflows.

4. Hardware Health (Thermals & Storage)

  • Thermals: If inference starts fast but slows down over time, call thermal_profile to check for frequency clipping or overheating.
  • Storage: If model loading is slow, call check_storage_health to verify if the model is on a slow HDD vs NVMe SSD.

Read the full file on GitHub · 53 lines

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. 6d ago First seen · 53 lines · 23 tokens per session scan A ab731d5d14aa

Subscribe to this mod's changes

local-inference-optimizer is a skill published in the GitHub repository yamaru-eu/hardware-probe (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 714 once invoked, about $0.0001 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

integrated-browser

Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.

microsoft/vscode · 68 tokens

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

amc-run-rtsp-calibration

Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.

NVIDIA/skills · 59 tokens