Your models. Your Mac.
An open-source EXL3 inference engine for macOS.
Run your models locally, in a native app or your terminal.
curl -fsSL https://mlxl3.0xzknw.tech/install.sh | bash
THE MAC APP
Chat, add your documents, connect MCP tools.
Your conversations stay on your Mac.
SUPPORTED MODELS
Import an EXL3 checkpoint or find one on Hugging Face.
The app checks its structure before loading.
Qwen3.5 / 3.6 / 3.8
Dense and MoE models with hybrid Gated DeltaNet attention. Text chat and MTP on supported checkpoints.
qwen3_5 · qwen3_5_moe
Liquid AILFM2 / LFM2 MoE
Recurrent-state models. The engine supports dense EXL3 weights and routed experts for text chat.
lfm2 · lfm2_moe
Gemma4
Text chat and native tool-call parsing. Image and audio inputs are not supported.
gemma4
Ling3 / Bailing V3
Text chat, hybrid architecture and MCP tool calls in Ling’s native format.
bailing_hybrid
The EXL3 format alone does not guarantee compatibility. Architecture, tensor shapes and engine requirements must also match.
THE ENGINE
EXL3 weights, read directly. Rust orchestrates inference; MLX and custom Metal kernels run it on Apple Silicon.
- EXL3
- Rust
- MLX
- Metal
On supported Qwen models, MTP proposes tokens and the target model verifies them before delivery.
MTP validationTHE COMMAND LINE
The same engine, in your terminal.
Inspect, register and run models with mlxl3.
# Replace the path with your EXL3 folder
mlxl3 register my-model /path/to/model
# Start a conversation
mlxl3 run my-modelInstall Desktop + CLI, then open a new terminal.
GET STARTED
The app includes its engine. No Python or Homebrew required.
-
Install the app.
Use the command above, or open the DMG and drag MLXL3 Desktop into Applications.
-
Choose a model.
Download an EXL3 variant from Hugging Face in the app, or import an existing folder.
-
Start a conversation.
Load the model and send your first message. Model weights are not included in the app download.
The current distribution is signed ad hoc. If macOS blocks the first launch, allow the app in System Settings → Privacy & Security.
A FEW DETAILS
Can I run EXL3 models on macOS?
On an Apple Silicon Mac, install MLXL3 Desktop, download or import a supported EXL3 checkpoint, then load the model. The desktop app includes its native engine; no Python, Homebrew or CUDA installation is required. Follow the installation steps.
Which EXL3 models are supported?
Supported architectures include Qwen 3.5, 3.6 and 3.8 (dense and MoE), Liquid AI LFM2 and LFM2 MoE, Gemma 4, and Ling 3 / Bailing V3. The loader checks tensor shapes and engine constraints before loading. An EXL3 file alone does not guarantee compatibility. See model support for the current scope.
Is MLXL3 a port of ExLlamaV3?
MLXL3 is an independent Apple Silicon runtime. ExLlamaV3 provides the EXL3 format and numerical reference. MLXL3 executes inference through Rust, MLX and custom Metal kernels on Apple GPUs. The third-party notices document the code’s provenance and licenses.
Which Macs are supported?
An Apple Silicon Mac (M1–M5) running macOS 26.2 or later. Memory requirements depend on the model, quantization and context. The project’s performance measurements are run on M5.
Does everything stay on my Mac?
Inference runs locally and conversations are saved on your Mac. Downloads and updates use the network. Enabled MCP tools may send requests to the services you configure.
Which documents can I attach?
Text-based PDFs, TXT, Markdown, CSV, JSON and code files. MLXL3 extracts their text; it does not analyze images. Scanned or protected PDFs need preparation first. The model’s context window remains the limit.
Is the project open source?
MLXL3’s code is available under the MIT license. Models and third-party components retain their own licenses.