What is model-builder?

A workflow for converting, inspecting, modifying, quantizing, and testing machine-learning models on Qualcomm hardware. Quantization changes model numbers to formats such as FP16 or INT8 to support device inference.

Use it to export models, create QNN or SNPE DLC files, patch unsupported operations, quantize models, and validate inference.

It provides a defined process for preparing custom ONNX or PyTorch models for Qualcomm runtimes and checking whether they work.

model-builder — Skill by qualcomm

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/qualcomm/qai-appbuilder/model-builder

Any agent

npx skills add qualcomm/qai-appbuilder --skill model-builder

Clone the repo

git clone --depth 1 https://github.com/qualcomm/qai-appbuilder

Made for: Claude Code, Codex.

Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,370 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin unknown 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	$0.00106	$0.04370
Opus 5	$0.00053	$0.02185
Sonnet 5	$0.00021	$0.00874
Haiku 4.5	$0.00011	$0.00437

Measured 3d ago against content hash 858c0208aa64, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

model-builder 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 3d ago.

The scan reads SKILL.md. This mod also ships 21 executable files (scripts/_host_arch.py, scripts/adb_runner.py, scripts/inference/infer_classify.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.

tools/qaiappbuilder/factory/chat_features/model-builder/SKILL.md · 134 lines

The source is not reproduced here

No licence file

Read it on GitHub

Files

What ships with it

52 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.

3d ago First seen · 134 lines · 106 tokens per session scan A 858c0208aa64

Subscribe to this mod's changes

model-builder is a skill published in the GitHub repository qualcomm/qai-appbuilder (200 stars, last pushed 3d ago), with no licence file. It adds 106 tokens to every session and 4,370 once invoked, about $0.0005 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 Hardware and IoT

nemo-mbridge-perf-memory-tuning

Techniques for reducing peak GPU memory in Megatron Bridge, including expandable segments, PEFT plus sequence-parallel input re-gather, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM fixes. Use for GPU OOMs, inadequate memory headroom, LoRA or PEFT activation pressure, memory…

NVIDIA-NeMo/Megatron-Bridge · 84 tokens

nemo-mbridge-perf-moe-hardware-configs

Representative, point-in-time MoE training playbooks by hardware and model family. Use them as candidate seeds, then revalidate the exact runtime, semantics, topology, and steady-state throughput.

NVIDIA-NeMo/Megatron-Bridge · 51 tokens

gguf-quantization

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

Orchestra-Research/AI-Research-SKILLs · 48 tokens

dstack-presets

Create and manage dstack presets: a toolkit that streamlines model inference optimization with agents, and a portable preset format. Use together with the dstack skill, and only when the user explicitly asks to create a preset or manage existing presets, not for deploying or serving a model.

dstackai/dstack · 61 tokens

KernelWiki

Use when the user asks about optimizing NVIDIA Blackwell (SM100, B200) or Hopper (SM90, H100) GPU kernels — tcgen05/TMEM/CLC/NVFP4/2-SM cooperative, warp specialization, FlashAttention-4, DeepGEMM, FlashMLA, MoE, grouped GEMM, CuTe-DSL/PTX/Triton on Blackwell, or wants concrete PR references from…

mit-han-lab/KernelWiki · 143 tokens

homeassistant-bridge

Bidirectional Home Assistant integration — HA cameras in, detection results out.

SharpAI/DeepCamera · 18 tokens