The best laya-mlx alternatives

laya-coreml

mizorewww/laya-coreml

Local Laya typed decisions on Apple Core ML and Neural Engine. Validated ports, ~5 ms short decisions on M3 Max, reproducible speed and energy benchmarks.

Choose laya-coreml if…

• you prefer a smaller, narrower project to a large one
• you specifically need apple-neural-engine or coreml

Shares apple-silicon, decision-model, laya, local-ai with laya-mlx.

mlx-vlm

Blaizzy/mlx-vlm

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

Choose mlx-vlm if…

• MIT License suits your use better than Apache License 2.0
• you specifically need florence2 or idefics

Shares apple-silicon, local-ai, mlx with laya-mlx.

claude-code-local

nicedreamzapp/claude-code-local

Run Claude Code 100% on-device with local AI on Apple Silicon. MLX-native Anthropic-API server. 6 fighters incl. Muse-Glimmer 30B (now multimodal — reads images, abliterated), Gemma 4 31B, Qwen 3.5 122B (65 tok/s), DeepSeek V4 Flash (1M ctx). Private, offline, airgap-ready. Built for NDA / legal / healthcare workflows.

Choose claude-code-local if…

• MIT License suits your use better than Apache License 2.0
• you prefer a smaller, narrower project to a large one
• you specifically need abliterated or ai-privacy

Shares apple-silicon, local-ai, mlx with laya-mlx.

inference

xorbitsai/inference

Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.

Choose inference if…

• you specifically need artificial-intelligence or deployment

Shares inference, machine-learning with laya-mlx.

MTPLX

youssofal/MTPLX

3x faster speeds on MLX | Qwen 3.8 27B | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.

Choose MTPLX if…

• you prefer a smaller, narrower project to a large one
• you specifically need anthropic-compatible or inference-engine

Shares apple-silicon, local-ai, mlx with laya-mlx.

Soup

MakazhanAlpamys/Soup

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

Choose Soup if…

• you specifically need cli or consumer-gpu

Shares local-ai, machine-learning with laya-mlx.

shimmy

Michael-A-Kuykendall/shimmy

⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.

Choose shimmy if…

• you would rather work in Rust than Python
• you specifically need api-server or command-line-tool

Shares local-ai, machine-learning with laya-mlx.

StartLux-Decision

StartLuxLabs/StartLux-Decision

Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.

Choose StartLux-Decision if…

• you prefer a smaller, narrower project to a large one
• you specifically need agents or calibration

Shares inference, mlx with laya-mlx.

AnyJev

nokia-applied-research/AnyJev

Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)

Choose AnyJev if…

• you prefer a smaller, narrower project to a large one
• you specifically need calibration or jev

Shares decision-model, system-one with laya-mlx.

vllm

vllm-project/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

Choose vllm if…

• you want the more widely starred option (96.8k)
• you specifically need amd or blackwell

Shares inference with laya-mlx.

Kiln

Kiln-AI/Kiln

Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

Choose Kiln if…

• you specifically need ai or chain-of-thought

Shares machine-learning with laya-mlx.

screenpipe

screenpipe/screenpipe

YC (S26) | Open Computer History | Record your screen continuously locally and provide context to your agents (Claude, Codex, Openclaw, Hermes, Runner...)

Choose screenpipe if…

• you would rather work in Rust than Python
• you want the more widely starred option (22.4k)
• you specifically need agents or agi

Shares local-ai, machine-learning with laya-mlx.