Source: https://seerepo.com/compare/mudler/LocalAI/vs/NVIDIA/TensorRT-LLM
Markdown source: https://seerepo.com/compare/mudler/LocalAI/vs/NVIDIA/TensorRT-LLM.md
Description: LocalAI and TensorRT-LLM share 24 technologies: MCP, OpenAI, anyio, FastAPI, uvicorn, matplotlib, accelerate, einops, flash-attn, sentencepiece, tiktoken, torchao, torchvision, torch, transformers, diffusers, librosa, datasets, optimum, peft, safetensors, pillow, jinja2, and OpenTelemetry. LocalAI is written in Go and TensorRT-LLM in Python.

# LocalAI vs TensorRT-LLM

LocalAI and TensorRT-LLM share 24 technologies: MCP, OpenAI, anyio, FastAPI, uvicorn, matplotlib, accelerate, einops, flash-attn, sentencepiece, tiktoken, torchao, torchvision, torch, transformers, diffusers, librosa, datasets, optimum, peft, safetensors, pillow, jinja2, and OpenTelemetry. LocalAI is written in Go and TensorRT-LLM in Python.

- [mudler/LocalAI](https://seerepo.com/r/mudler/LocalAI): LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
- [NVIDIA/TensorRT-LLM](https://seerepo.com/r/NVIDIA/TensorRT-LLM): TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

## What they share and what sets them apart

- In common: MCP, OpenAI, anyio, FastAPI, uvicorn, matplotlib, accelerate, einops, flash-attn, sentencepiece, tiktoken, torchao, torchvision, torch, transformers, diffusers, librosa, datasets, optimum, peft, safetensors, pillow, jinja2, OpenTelemetry
- Only in LocalAI: React, net/http, Echo, pyarrow, s3, NATS.io, Postgres, github.com/glebarez/sqlite, SQLite, Hugging Face, Lightning, Tokio, react-router-dom, Vite, Gradio, gorm.io/gorm, github.com/nats-io/jwt/v2, github.com/nats-io/nkeys, golang.org/x/oauth2, github.com/aws/aws-sdk-go-v2/credentials, github.com/coreos/go-oidc/v3, bitsandbytes, conformer, coqui-tts, llama-cpp-python, llvmlite, Model Context Protocol, ModelScope, ONNX, onnxruntime-gpu, openai-go, phonemizer, s3tokenizer, scikit-image, spacy-pkuseg, vector-quantize-pytorch, mlx, opencv-python, insightface, mlx-lm, torchaudio, vLLM, onnxruntime, sglang, faster-whisper, funasr, kokoro, mlx-audio, QWen, rerankers, sentence-transformers, tokenizers, trl, whisperx, av, sox, torchcodec, github.com/go-audio/wav, github.com/charmbracelet/glamour, github.com/dhowden/tag, github.com/microcosm-cc/bluemonday, golang.org/x/image, imageio, imageio-ffmpeg, loguru, go.opentelemetry.io/otel/metric, Docker, tracing, github.com/aws/aws-sdk-go-v2, github.com/aws/aws-sdk-go-v2/config, github.com/Microsoft/hcsshim, go.opentelemetry.io/otel/exporters/prometheus, go.opentelemetry.io/otel/sdk/metric, Prometheus, tracing-subscriber, fontsource-variable, CodeMirror, @lezer/highlight, yaml, dompurify, highlight.js, marked
- Only in TensorRT-LLM: blobfile, h5py, pyzmq, starlette, Rich, Plotly, apache-tvm-ffi, cuda-python, flash-linear-attention, flashinfer-python, NVIDIA, nvidia-cudnn-frontend, openai-codex, openai-harmony, quack-kernels, rouge, rouge-score, torch-c-dlpack-ext, triton, xgrammar, mistral-common, partial-json-parser, tritonclient, evaluate, llguidance, lm-eval, jsonlines, mako, Pydantic, msgspec, jsonschema, opentelemetry-api, opentelemetry-semantic-conventions-ai, psutil, prometheus-client, boto3, opentelemetry-sdk, prometheus-fastapi-instrumentator

## Side by side

| | LocalAI | TensorRT-LLM |
|---|---|---|
| Size | 1,389,292 lines written, 2,979 code files | 2,884,778 lines written, 3,120 code files |
| Who writes it | 3.7% of its commits signed by AI. With Claude Code, GitHub Copilot, and Cursor | 1.7% of its commits signed by AI. With Claude Code, CodeRabbit, GitHub Copilot, and Cursor |
| Activity | Last push November 5, 2026, 9,317 commits, 50,214 stars | Last push November 8, 2026, 10,997 commits, 15,038 stars |
| Tests | 2,911 test files. 60.8% of its code files have a test that imports them | 2,703 test files. 58.6% of its code files have a test that imports them |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, LocalAI or TensorRT-LLM?

TensorRT-LLM, with 2,884,778 lines written; LocalAI has 1,389,292.

The proof: [NVIDIA/TensorRT-LLM's code at commit b433473](https://github.com/NVIDIA/TensorRT-LLM/tree/b433473ba0d0d49764f4d2fb3d45c82716b946dc)

### Which has more GitHub stars, LocalAI or TensorRT-LLM?

LocalAI, with 50,214 stars; TensorRT-LLM has 15,038.

The proof: [mudler/LocalAI on GitHub](https://github.com/mudler/LocalAI)

### Which has more tests, LocalAI or TensorRT-LLM?

LocalAI, with 2,911 test files; TensorRT-LLM has 2,703.

The proof: [mudler/LocalAI's code at commit efc6f93](https://github.com/mudler/LocalAI/tree/efc6f9373ffd35c87cf45e334cdbf7f5f19076f6)

### Which was updated more recently, LocalAI or TensorRT-LLM?

TensorRT-LLM: its last push was on November 8, 2026, and LocalAI's on November 5, 2026.

The proof: [NVIDIA/TensorRT-LLM's commits on GitHub](https://github.com/NVIDIA/TensorRT-LLM/commits)

### Which has more commits signed by AI, LocalAI or TensorRT-LLM?

LocalAI: an AI signed 3.7% of its commits, with Claude Code, GitHub Copilot, and Cursor; in TensorRT-LLM, 1.7%.

The proof: [the commits each tool signed in mudler/LocalAI](https://seerepo.com/r/mudler/LocalAI/ai)

## Sources

- mudler/LocalAI: Read on November 5, 2026, at commit efc6f93 (https://github.com/mudler/LocalAI/tree/efc6f9373ffd35c87cf45e334cdbf7f5f19076f6)
- NVIDIA/TensorRT-LLM: Read on November 8, 2026, at commit b433473 (https://github.com/NVIDIA/TensorRT-LLM/tree/b433473ba0d0d49764f4d2fb3d45c82716b946dc)

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.