quantized-llama2-7b-mlc

quantized-llama2-7b-mlc is a skill for Claude Code, Codex from Seeed-Projects/Seeed-Jetson-DevelopTool. It costs 82 tokens per session (1,216 once invoked), scanned B, original, MIT.

A guide for running a smaller, compressed version of Meta’s Llama 2 language model directly on a Jetson Orin. The model can generate text locally without sending prompts to a remote service.

In plain words
What is it for?
Use it to install and run Llama2-7B with MLC LLM and jetson-containers using four-bit model quantization on a Jetson with at least 16 GB of RAM.
Why use it?
It explains the hardware, storage, access-token, Docker, and model-download requirements for this specific setup.

Skill for Claude CodeCodex

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

Good fit Use it to install and run Llama2-7B with MLC LLM and jetson-containers using four-bit model quantization on a Jetson with at least 16 GB of RAM.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/seeed-projects/seeed-jetson-developtool/quantized-llama2-7b-mlc
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 Seeed-Projects/Seeed-Jetson-DevelopTool --skill quantized-llama2-7b-mlc
Clone the repo
git clone --depth 1 https://github.com/Seeed-Projects/Seeed-Jetson-DevelopTool

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 quantized-llama2-7b-mlc

README.md
[![agentmods](https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/quantized-llama2-7b-mlc.svg)](https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/quantized-llama2-7b-mlc)
Your own site
<a href="https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/quantized-llama2-7b-mlc"><img src="https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/quantized-llama2-7b-mlc.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,216 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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: 7 findings, up to high

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 →

  • high Privilege Escalation · line 3
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 28
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium MCP Rug Pull · line 27
    Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
    Fix: Pin the image: image:tag or image@sha256:abc123
  • medium Privilege Escalation · line 47
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Privilege Escalation · line 48
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Privilege Escalation · line 78
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Privilege Escalation · line 135
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00082 $0.01216
Opus 5 $0.00041 $0.00608
Sonnet 5 $0.00016 $0.00243
Haiku 4.5 $0.00008 $0.00122

Measured 5d ago against content hash 384e710d53f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

quantized-llama2-7b-mlc scanned grade B 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 5d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo apt-get update
seeed_jetson_develop/skills/openclaw/quantized-llama2-7b-mlc/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quantized Llama2-7B with MLC LLM on Jetson


Execution model

Run one phase at a time. After each phase:

  • Relay all command output to the user.
  • If output contains [STOP] → stop immediately, consult the failure decision tree below.
  • If output ends with [OK] → tell the user "Phase N complete" and proceed to the next phase.

Prerequisites

Requirement Minimum
Hardware reComputer J4012 (Jetson Orin NX 16GB) or equivalent
RAM ≥ 16 GB
JetPack 5.x (R35.x)
Storage SSD recommended — model weights + Docker images are large
Internet Required for Docker pull and model download
HuggingFace Access token with Llama2 model access granted

Phase 1 — Preflight

cat /etc/nv_tegra_release
free -h
df -h /

Expected: R35.x (JP5), ≥16 GB RAM, ≥50 GB disk free. [OK] when all pass. [STOP] if insufficient RAM or disk.


Phase 2 — Install dependencies and clone jetson-containers

sudo apt-get update
sudo apt-get install -y git python3-pip
git clone --depth=1 https://github.com/dusty-nv/jetson-containers
cd jetson-containers
pip3 install -r requirements.txt

Clone the MLC-LLM helper scripts:

cd ./data
git clone https://github.com/LJ-Hao/MLC-LLM-on-Jetson-Nano.git
cd ..

[OK] when both repos are cloned and requirements installed. [STOP] if git clone fails.


Phase 3 — Pull MLC Docker image and download Llama2 model

Replace <YOUR-ACCESS-TOKEN> with your HuggingFace token:

./run.sh --env HUGGINGFACE_TOKEN=<YOUR-ACCESS-TOKEN> $(./autotag mlc) \
  /bin/bash -c 'ln -s $(huggingface-downloader meta-llama/Llama-2-7b-chat-hf) /data/models/mlc/dist/models/Llama-2-7b-chat-hf'

Verify the Docker image was created:

sudo docker images | grep mlc

[OK] when MLC image is listed and model download completed. [STOP] if image not found or download failed.


Phase 4 — Quantize the model with MLC

./run.sh $(./autotag mlc) \
  python3 -m mlc_llm.build \
  --model Llama-2-7b-chat-hf \
  --quantization q4f16_ft \
  --artifact-path /data/models/mlc/dist \
  --max-seq-len 4096 \
  --target cuda \
  --use-cuda-graph \
  --use-flash-attn-mqa

Read the full file on GitHub · 146 lines

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. 5d ago First seen · 146 lines · 82 tokens per session scan B 384e710d53f5

Subscribe to this mod's changes

quantized-llama2-7b-mlc is a skill published in the GitHub repository Seeed-Projects/Seeed-Jetson-DevelopTool (54 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 1,216 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

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