expert-llmfit

expert-llmfit is a skill for Claude Code, Codex from yamaru-eu/hardware-probe. It costs 46 tokens per session (891 once invoked), scanned C, original, Apache-2.0.

A skill for checking and maintaining hardware recommendations for running language models locally, using model size, memory needs, memory bandwidth, and running mode.

In plain words
What is it for?
Use it when updating or verifying the LlmFitEngine, estimating VRAM or RAM needs, or comparing GPU, CPU, and mixed-running options.
Why use it?
It helps keep recommendations aligned with the upstream LLMFit project and avoid mismatching a model with available computer hardware.

Skill for Claude CodeCodex

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

Good fit Use it when updating or verifying the LlmFitEngine, estimating VRAM or RAM needs, or comparing GPU, CPU, and mixed-running options.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yamaru-eu/hardware-probe/expert-llmfit
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 yamaru-eu/hardware-probe --skill expert-llmfit
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 expert-llmfit

README.md
[![agentmods](https://agentmods.dev/badge/skills/yamaru-eu/hardware-probe/expert-llmfit/github.svg)](https://agentmods.dev/skills/yamaru-eu/hardware-probe/expert-llmfit)
Your own site
<a href="https://agentmods.dev/skills/yamaru-eu/hardware-probe/expert-llmfit"><img src="https://agentmods.dev/badge/skills/yamaru-eu/hardware-probe/expert-llmfit/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 expert-llmfit

Your own site · 80×15
<a href="https://agentmods.dev/skills/yamaru-eu/hardware-probe/expert-llmfit"><img src="https://agentmods.dev/badge/skills/yamaru-eu/hardware-probe/expert-llmfit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 891 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00046 $0.00891
Opus 5 $0.00023 $0.00445
Sonnet 5 $0.00009 $0.00178
Haiku 4.5 $0.00005 $0.00089

Measured 10d ago against content hash d06a3551bb13, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

expert-llmfit scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf /tmp/llmfit_external
skills/expert-llmfit/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Expert LLMFit (BETA)

This skill provides the domain expertise required to maintain the LlmFitEngine inside remote-affiliate-api/src/core/llmfit.engine.ts and keep it synchronized with the upstream logic from https://github.com/AlexsJones/llmfit.

Core Concepts & Formulas

  1. Inference is Memory-Bandwidth-Bound:

    • Theoretical Max TPS = Memory Bandwidth (GB/s) / Model Size (GB)
    • Real TPS Estimate = Max TPS * Efficiency Factor (0.55) * RunMode Penalty.
    • The efficiency factor (0.55) accounts for kernel launch overhead and KV-cache reads.
  2. RunMode Penalties:

    • gpu: 1.0 (Full speed)
    • moe_offload: 0.8 (Expert switching latency)
    • cpu_gpu: 0.5 (Partial offload penalty)
    • cpu_only: 0.3 (Fallback to slow RAM)
  3. Memory Requirements (VRAM/RAM):

    • Base Model Size = Parameters * BytesPerParam
      • FP16/BF16: 2.0 bytes
      • Q8: 1.0 byte
      • Q4_K_M: 0.5 bytes (Standard for local inference recommendations)
    • KV Cache Overhead: Context length requires additional VRAM.
    • Rule of Thumb VRAM: (Model Size in GB * 1.2) to account for context and OS overhead.
  4. Mixture of Experts (MoE):

    • Fit/VRAM checks use Total Parameters.
    • Speed/TPS estimates use Active Parameters (e.g., Mixtral 8x7B uses ~12.9B active params per token).

Verification & Adaptation Workflow

Whenever asked to "verify LLMFit logic" or "update the hardware recommendation engine", follow these steps:

Step 1: Upstream Sync

  • Clone the upstream repository into a temporary directory:
    mkdir -p /tmp/llmfit_external && git clone https://github.com/AlexsJones/llmfit /tmp/llmfit_external
    
  • Inspect key Rust files:
    • llmfit-core/src/fit.rs (for TPS and scoring formulas).
    • llmfit-core/src/hardware.rs (for GPU bandwidth updates and compute capabilities).
    • llmfit-core/src/models.rs (for Quantization multipliers and MoE active parameters).

Step 2: Codebase Audit (remote-affiliate-api)

  • Compare the upstream formulas with our local TypeScript implementation in src/core/llmfit.engine.ts.
  • Ensure the estimateTokensPerSecond method correctly applies the 0.55 efficiency factor and RunMode penalties.
  • Verify calculateRequiredMemory properly uses active vs total parameters.

Read the full file on GitHub · 69 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. 10d ago First seen · 69 lines · 46 tokens per session scan C d06a3551bb13

Subscribe to this mod's changes

expert-llmfit is a skill published in the GitHub repository yamaru-eu/hardware-probe (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 891 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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

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

deepstream-import-vision-model

Use this skill to bring a supported object-detection vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT engine build, custom nvinfer bbox parser, multi-stream benchmark, and PDF report. Object detection models only.

NVIDIA/skills · 72 tokens