mlc-llm vs LocalAI
mlc-llm and LocalAI share 9 technologies: FastAPI, uvicorn, datasets, OpenAI, sentencepiece, transformers, safetensors, tiktoken, and torch. mlc-llm is written in Python and LocalAI in Go.
What they share and what sets them apart
mlc-ai
mlc-llm
Universal LLM Deployment Engine with ML Compilation
Python23.3kRead on November 4, 2026, at commit 44fd06dWhat is mlc-llm built with?Only in mlc-llm
- Jetpack Compose
- androidx.core:core-ktx
- androidx.navigation:navigation-compose
- lifecycle-runtime-ktx
- appcompat
- com.google.android.material:material
- ui-graphics
- MarkdownUI
prompt-toolkit
- androidx.compose.material:material-icons-extended
- apache-tvm-ffi
- flashinfer-python
In common
mudler
LocalAI
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Go50.2kRead on November 5, 2026, at commit efc6f93What is LocalAI built with?Only in LocalAI
- React
- net/http
- Echo
pyarrow
s3
- NATS.io
- Postgres
- github.com/glebarez/sqlite
- SQLite
- MCP
- Hugging Face
- anyio
- Lightning
- Tokio
react-router-dom
- Vite
- Gradio
matplotlib
- 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
accelerate
- bitsandbytes
- conformer
- coqui-tts
- einops
- flash-attn
llama-cpp-python
- llvmlite
- Model Context Protocol
- ModelScope
- ONNX
- onnxruntime-gpu
openai-go
- phonemizer
- s3tokenizer
scikit-image
- spacy-pkuseg
torchao
torchvision
- vector-quantize-pytorch
diffusers
mlx
opencv-python
insightface
- mlx-lm
torchaudio
- vLLM
librosa
- onnxruntime
sglang
- faster-whisper
funasr
- kokoro
- mlx-audio
optimum
peft
- QWen
- rerankers
sentence-transformers
tokenizers
trl
- whisperx
av
- sox
- torchcodec
github.com/go-audio/wav
pillow
github.com/charmbracelet/glamour
- github.com/dhowden/tag
github.com/microcosm-cc/bluemonday
- golang.org/x/image
imageio
imageio-ffmpeg
- jinja2
loguru
- go.opentelemetry.io/otel/metric
- OpenTelemetry
- 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
Side by side
mlc-llmLocalAI
SizeLines written by people and agents, without generated ones; code files, without tests.
mlc-llm80,952 lines written325 code files
LocalAI1,389,292 lines written2,979 code files
Who writes itA commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
mlc-llm0.2% of its commits signed by AIWith Claude Code, Gemini CLI, and GitHub Copilot
LocalAI3.7% of its commits signed by AIWith Claude Code, GitHub Copilot, and Cursor
ActivityFrom GitHub and its history, on the day SeeRepo read it.
mlc-llmLast push October 30, 20261,823 commits23,302 stars
LocalAILast push November 5, 20269,317 commits50,214 stars
TestsThe files that test the code, and the share of code files a test imports.
mlc-llm69 test files16.3% of its code files have a test that imports them
LocalAI2,911 test files60.8% of its code files have a test that imports them
Frequently asked questions
Which is bigger, mlc-llm or LocalAI?
LocalAI, with 1,389,292 lines written; mlc-llm has 80,952.
The proof: mudler/LocalAI's code at commit efc6f93
Which has more GitHub stars, mlc-llm or LocalAI?
LocalAI, with 50,214 stars; mlc-llm has 23,302.
The proof: mudler/LocalAI on GitHub
Which has more tests, mlc-llm or LocalAI?
LocalAI, with 2,911 test files; mlc-llm has 69.
The proof: mudler/LocalAI's code at commit efc6f93
Which was updated more recently, mlc-llm or LocalAI?
LocalAI: its last push was on November 5, 2026, and mlc-llm's on October 30, 2026.
The proof: mudler/LocalAI's commits on GitHub
Which has more commits signed by AI, mlc-llm or LocalAI?
LocalAI: an AI signed 3.7% of its commits, with Claude Code, GitHub Copilot, and Cursor; in mlc-llm, 0.2%.
See inside your code, today.
Paste your repo and see it drawn, part by part: a medium one in under a minute.
Free, no account.

