project-maya

project-maya is a local inference server - Project Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.

Overview

GLM-5.3-Flash (321 B), DeepSeek-V4.1-Flash-1017 (748 B) and MiniMax-M3.1-Flash (428 B) on your own GPU private and fast · one NVIDIA GPU or up to 16 · AMD and Windows (experimental) · chat, pictures, OpenAI- and Anthropic-compatible API · several requests at once

Project Maya is free. If it runs well on your PC, sponsoring it pays for the test hardware and the work on it.

Models this size usually need a datacenter. Maya runs three of them on the hardware you already have: GLM-5.3-Flash, DeepSeek-V4.1-Flash-1017 and MiniMax-M3.1-Flash. Each model has an engine built for it. It keeps the experts your conversation uses most on the GPU, the next ones in RAM and the rest on your NVMe SSD, and moves them as you chat. It measures your GPUs, CPU, RAM and SSD and tunes itself to them. Nothing leaves your machine.

project-maya is open-source, written primarily in Cuda, with 2,289 GitHub stars under the MIT license. The latest release is v1.1.42 (2026-10-30).

Key capabilities

From the project's documentation:

• Fast: up to 149 tokens/s on two RTX 5090s and an RTX 4090, 124 on two H100s, 118 on four RTX 4090s, 81 on one
• Close to the original: Maya's own quants of GLM-5.3-Flash keep 97.7-99.2% of the FP8 model's zero-shot
• Plugs into your tools: OpenAI- and Anthropic-compatible API with tool calls, ready for coding agents.
• Several requests at once: up to 8 answered together with GLM-5.3-Flash, DeepSeek-V4.1-Flash and
• Everything in the box: a chat and a live monitor in the browser, pictures, thinking levels, a one-command setup.
• GLM-5.3 · Maya quants keep 97.7-99.2% of the FP8 model's zero-shot accuracy and pick its next token 83-90% of

How it fits a local-AI stack

project-maya runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related local inference servers in the directory:

• "BentoML"
• "candle-vllm"
• "CTranslate2"
• ExLlamaV2

Sources

• Source code & docs: mw00/project-maya
• Official website: https://huggingface.co/peasantsmith

Stats from GitHub, 2026-10-30.