What is synthesis-local-model-runtime?

A guide to selecting and managing open-weight AI models that run on a personal computer. It checks the computer’s memory and storage, compares local runtimes such as Ollama and LM Studio, and plans approved installations.

Use it to profile a machine, compare local model runtimes, recommend compatible model files and quantizations, create a dry-run installation plan, and update Ollama models with before-and-after records.

A model may fail to run or consume too much space if it does not fit the computer or runtime settings. This helps base choices on measured capacity and documented model artifacts.

synthesis-local-model-runtime — Skill for Claude Code and Codex by syn

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 synthesisengineering/synthesis-skills --skill synthesis-local-model-runtime

Clone the repo

git clone --depth 1 https://github.com/synthesisengineering/synthesis-skills

Made for: Claude Code, Codex.

Or install synthesis-skills, the plugin that ships this one along with the rest of its 63 skills, 4 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-local-model-runtime/github.svg)](https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-local-model-runtime)

Your own site

<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-local-model-runtime"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-local-model-runtime/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-local-model-runtime"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-local-model-runtime.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 135 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,871 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Rogue Agent · line 30
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
medium Rogue Agent · line 182
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00135	$0.02871
Opus 5	$0.00068	$0.01435
Sonnet 5	$0.00027	$0.00574
Haiku 4.5	$0.00014	$0.00287

Measured 9d ago against content hash 4839539f03be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

synthesis-local-model-runtime 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 9d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/local_model_runtime.py, scripts/test_local_model_runtime.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/synthesis-local-model-runtime/SKILL.md · 294 lines

How it starts

The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Synthesis Local Model Runtime

Select local models from measured capacity and dated artifact evidence. Do not turn a model name, parameter count, vendor origin, or successful launch into a claim that an artifact is safe, private, independent, unmarked, or suitable for every workload.

Operating contract

Profile the machine with scripts/local_model_runtime.py profile. The profiler emits only selection-relevant fields. It never emits hostnames, serial numbers, hardware UUIDs, provisioning identifiers, or account data.
Validate the bundled catalog before using it: scripts/local_model_runtime.py catalog.
Inspect runtimes and choose a managed environment. Ollama is the default; LM Studio is the optional managed alternative. llama.cpp and MLX-LM are reported as direct runtimes with their actual capability boundaries.
Load any local policy and create a dry-run plan. Recommendation applies exclusions first, then hard memory, storage, and runtime-configuration gates, then quality ordering.
Present the exact artifacts, quantizations, distribution channels, disk estimate, remaining free space, runtime prerequisites, and reasons.
Install only after the user authorizes the downloads. install is dry-run unless --yes is supplied.
Verify the runtime's resolved artifact metadata. Record what actually installed, not what the catalog predicted.
Update installed Ollama models only through an explicit model list or explicit --all. update is dry-run unless --yes is supplied and records both identities even when the pull is an already-current no-op.
Run bounded functional and performance checks one model at a time. Unload each model after testing.
Update the per-machine inventory only after verified state transitions. Separate installation commands merge their verified selections; an explicit inventory refresh replaces selections with the current plan.
When a Hugging Face registry pull fails after catalog-pinned GGUF layers are cached, permit the deterministic local-import recovery only after every full digest and exact size matches. Never import an unpinned partial download.

Read the full file on GitHub · 294 lines

Files

What ships with it

8 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.

9d ago First seen · 294 lines · 135 tokens per session scan A 4839539f03be

Subscribe to this mod's changes

synthesis-local-model-runtime is a skill published in the GitHub repository synthesisengineering/synthesis-skills (18 stars, last pushed 2d ago), licensed Apache-2.0. It adds 135 tokens to every session and 2,871 once invoked, about $0.0007 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 2026-08-30.

Data and AI

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens