The best laya-coreml alternatives

laya-mlx

mizorewww/laya-mlx

Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.

Choose laya-mlx if…

• you want the more widely starred option (7.1k)
• you specifically need inference or machine-learning

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

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 want the more widely starred option (3.5k)
• you specifically need abliterated or ai-privacy

Shares apple-silicon, local-ai, on-device-ai with laya-coreml.

turbo-fieldfare

drumih/turbo-fieldfare

Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

Choose turbo-fieldfare if…

• you would rather work in Swift than Python
• you want the more widely starred option (7.3k)
• you specifically need gemma or gemma4

Shares apple-silicon, local-ai, on-device-ai with laya-coreml.

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 want the more widely starred option (5.8k)
• you specifically need florence2 or idefics

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

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 want the more widely starred option (2.7k)
• you specifically need anthropic-compatible or inference-engine

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

ODS

Osmantic/ODS

Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation.

Choose ODS if…

• you want the more widely starred option (7.8k)
• you specifically need ai-agents or amd

Shares local-ai with laya-coreml.

GenieX

qualcomm/GenieX

Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

Choose GenieX if…

• you would rather work in Rust than Python
• BSD 3-Clause "New" or "Revised" License suits your use better than Apache License 2.0
• you want the more widely starred option (8.5k)
• you specifically need gemma4 or go

Shares local-ai, on-device-ai with laya-coreml.

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 want the more widely starred option (10.5k)
• you specifically need cli or consumer-gpu

Shares local-ai with laya-coreml.

omlx

jundot/omlx

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

Choose omlx if…

• you want the more widely starred option (23.6k)
• you specifically need inference-server or llm

Shares apple-silicon with laya-coreml.

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 want the more widely starred option (6.0k)
• you specifically need api-server or command-line-tool

Shares local-ai with laya-coreml.

OGAM

off-grid-ai/OGAM

The Swiss Army Knife of Offline AI. Chat, see, speak, and generate images on your phone or Mac — GGUF LLMs, vision, Whisper speech-to-text, Stable Diffusion, tool calling, and local-network servers. Runs on your CPU, GPU, or NPU. No account, no API key, zero data leaves your device.

Choose OGAM if…

• you would rather work in TypeScript than Python
• MIT License suits your use better than Apache License 2.0
• you want the more widely starred option (3.4k)
• you specifically need android or edge-ai

Shares local-ai with laya-coreml.

lucebox

Luce-Org/lucebox

LLM speculative inference server for heterogeneous hardware & consumer GPUs

Choose lucebox if…

• you would rather work in C++ than Python
• you want the more widely starred option (3.0k)
• you specifically need cuda or cuda-kernels

Shares local-ai with laya-coreml.