minicpm5-deploy-litert

minicpm5-deploy-litert is a skill for Claude Code, Codex from OpenBMB/MiniCPM. It costs 121 tokens per session (1,532 once invoked), scanned A, original, Apache-2.0.

Instructions for running MiniCPM5 language models on phones, desktops, and other devices with Google's LiteRT-LM runtime. LiteRT-LM runs packaged models through command-line, server, Python, Kotlin, or Swift interfaces.

In plain words
What is it for?
It helps install LiteRT-LM, run a .litertlm model, start an OpenAI-compatible server, and use the model from desktop or mobile code.
Why use it?
It turns the model files and runtime choices into concrete setup steps, including CPU or GPU use and Android deployment.

Skill for Claude CodeCodex

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

Good fit It helps install LiteRT-LM, run a .litertlm model, start an OpenAI-compatible server, and use the model from desktop or mobile code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/openbmb/minicpm/minicpm5-deploy-litert
About the project

MiniCPM is a family of compact language models, including MiniCPM5-1B, designed to run locally on devices with limited resources. Developers use it for on-device assistants, reasoning, code, tool use, deployment, and fine-tuning, while the repository also includes a desktop-pet example. The catalogue entries support deployment and fine-tuning workflows for the models.

OpenBMB/MiniCPM · 10,780 stars · on GitHub

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 OpenBMB/MiniCPM --skill minicpm5-deploy-litert
Clone the repo
git clone --depth 1 https://github.com/OpenBMB/MiniCPM

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 minicpm5-deploy-litert

README.md
[![agentmods](https://agentmods.dev/badge/skills/openbmb/minicpm/minicpm5-deploy-litert/github.svg)](https://agentmods.dev/skills/openbmb/minicpm/minicpm5-deploy-litert)
Your own site
<a href="https://agentmods.dev/skills/openbmb/minicpm/minicpm5-deploy-litert"><img src="https://agentmods.dev/badge/skills/openbmb/minicpm/minicpm5-deploy-litert/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 minicpm5-deploy-litert

Your own site · 80×15
<a href="https://agentmods.dev/skills/openbmb/minicpm/minicpm5-deploy-litert"><img src="https://agentmods.dev/badge/skills/openbmb/minicpm/minicpm5-deploy-litert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,532 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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 $0.00121 $0.01532
Opus 5 $0.00060 $0.00766
Sonnet 5 $0.00024 $0.00306
Haiku 4.5 $0.00012 $0.00153

Measured today against content hash a3dea7288140, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

minicpm5-deploy-litert scanned grade A 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 today.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://127.0.0.1:9379/v1/chat/completions -H "Content-Type: application/json" \
skills/minicpm5-deploy-litert/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deploy MiniCPM5-2B / MiniCPM5-1B with LiteRT-LM (Android / iOS / desktop / IoT)

LiteRT-LM, Google's on-device runtime built on LiteRT (formerly TensorFlow Lite). One .litertlm bundle, CPU or GPU, through a CLI, an OpenAI-compatible server, Python, Kotlin and Swift. The bundles are hosted in litert-community. Human-readable reference: docs/deployment/litert.md.

Required input

Var Example Default
LITERT_REPO litert-community/MiniCPM5-2B or litert-community/MiniCPM5-1B litert-community/MiniCPM5-2B
FILE MiniCPM5-2B_int4.litertlm (1.55 GB, the phone file) or MiniCPM5-2B_int8.litertlm (2.60 GB, reasoning that has to finish); 1B: minicpm_wi4b32_wi8_afp32.litertlm (CPU) or minicpm_wi4b32_wi8_afp32_gpu_opt.litertlm (GPU) MiniCPM5-2B_int4.litertlm
BACKEND cpu or gpu cpu
THINKING true (reason first) or false (direct answer) false
PROMPT 1+1=? 1+1=?

Steps

1. Install (once)

uv tool install litert-lm

2A. Run a pre-converted bundle (desktop CLI)

litert-lm run --from-huggingface-repo="${LITERT_REPO}" "${FILE}" \
    --backend "${BACKEND}" --thinking "${THINKING:-false}" --prompt "${PROMPT}"

The first run downloads the file into ~/.litert-lm/cache/huggingface/<repo>/; later runs skip the download. With thinking on, the reasoning prints between [thought] and [/thought] and the answer follows; --thinking-budget 2048 caps the reasoning (4096 for math); THINKING=true makes the model reason first. Sampling as OpenBMB recommends: --top-k 40 --top-p 0.95 --temperature 1.0 (the CLI's default top-k is 1 = greedy, so temperature alone changes nothing).

2B. Android

  • No code: the AI Edge Gallery app, Model manager → +Import from HF → paste the file's Hugging Face link.
  • Your own app: implementation("com.google.ai.edge.litertlm:litertlm-android:0.17.0") from Google Maven, the libOpenCL.so <uses-native-library> entries in the manifest for the GPU, then:

Read the full file on GitHub · 80 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. today First seen · 80 lines · 121 tokens per session scan A a3dea7288140

Subscribe to this mod's changes

minicpm5-deploy-litert is a skill published in the GitHub repository OpenBMB/MiniCPM (10,780 stars, last pushed yesterday), licensed Apache-2.0. It adds 121 tokens to every session and 1,532 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-10.

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

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