NVIDIA/Model-Optimizer

5.2k starsPython Latest
Open on GitHub

What It Calls

Calls external APIs · local option Cloud by default Can switch to local Partial check

Without a key: Text generation · Image generation · Speech-to-text · Text-to-speech · Embeddings (OpenAI): has a branch that stops with an error without a key. Runs locally (Diffusers): runs locally (Diffusers). Local model file: runs locally (model file). The other rows are in the table below.

Feature matrix
Feature Provider Use Default Alternative
Text generation · Image generation · Speech-to-text · Text-to-speech · Embeddings OpenAI
3 call sites
Optional api.openai.com Configurable address
Runs locally (Diffusers) Local (Diffusers)
1 call sites
Local - -
Local model file Local (model file)
1 call sites
Local - -
Runs locally (ONNX Runtime) Local (ONNX Runtime)
1 call sites
Local - -
Runs locally (PyTorch) Local (PyTorch)
1 call sites
Local - -
Runs locally (Hugging Face Transformers) Local (Hugging Face Transformers)
1 call sites
Local - -
Runs locally (vLLM) Local (vLLM)
1 call sites
Local - -
External APIs
API Credential Code evidence Pricing Pricing page Checked
OpenAI Your API key tools/launcher/common/query.py:48It uses OpenAI by default, but the address can be changed to a local server. Paid Pricing 2026-10-05

Data sent out: prompt text

Checked scope: 1,653/2,342 files checked · deep read (up to 2,000 files) · tree not truncated · 1 submodule(s) not checked · 431 unresolved import path(s) · 26 files in languages not read (CUDA, C++, C)

Next

Check another repository This result is wrong

Badge preview

external API badge

[![external API](https://whatitcalls.com/badge/NVIDIA/Model-Optimizer.svg)](https://whatitcalls.com/en/NVIDIA/Model-Optimizer)

Shows as “external API · used · local option” in a README.

Was this analysis helpful?

Freshness detailscommit f299f62 · checked 2026-10-09
Committed
2026-10-09 02:38 UTC
Checked
2026-10-09 05:06 UTC
HEAD last seen
2026-10-09 04:45 UTC · f299f62 (same as the checked commit)
Read depth
Deep (up to 2,000 files · 64 MB)
Scanner · rules
scan-5+verdict-5
Pricing catalog
version 2
Correction revision
0
Summary
Model ollama-cloud/gemma4:31b-cloud
What is sent out
README claims ↔ code

No README claim contradicts the code.

Code quotes

Source files are not stored. Code is linked at the checked commit on GitHub; stored quotes are at most 3 lines per evidence and 6 per file.

Source: NVIDIA/Model-Optimizer · commit f299f62 · tools/launcher/common/query.py

Checked scope details

Files

In the repository
2,342
Checked
1,653 (70%)

Manifests

All priority files read

  • pyproject.toml
  • examples/gpt-oss/requirements.txt
  • examples/llm_eval/requirements.txt
  • examples/onnx_ptq/requirements-evaluator.txt
  • examples/speculative_decoding/requirements.txt
  • examples/torch_onnx/requirements.txt

+12 more

Unresolved import paths (431)

missing file 395 · importlib 16 · getattr module 15 · dynamic file load 2 · plugin discovery 2 · __import__ 1

Excluded files

  • .yaml 211
  • .md 192
  • .sh 62
  • .rst 46
  • .png 23
  • (none) 19

+19 more

External code not checked
Submodules tools/launcher/modules/Megatron-LM
Limits hit
None
Files in languages not read
CUDA 13 · C++ 8 · C 5
Symbolic links not followed
33
Correction history

No corrections yet.

This result is wrong · Corrections policy